AI And Analytics Course

AI And Analytics Course — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Threat actor

  In cybersecurity and risk assessment, a threat actor (or threat agents, attackers, or adversaries) is a person, group, organisation, state, or other entity with the ability to cause, carry, transmit, support, or exploit a threat. Threat actors are commonly analysed according to their motivations, resources, technical capability, access to systems, relationship to a target, and degree of connection to state authority. They may exploit vulnerabilities, conduct social engineering, steal or monetise data, disrupt operations, or support other actors who carry out such activity. Because the term covers a wide range of actors, researchers and security organisations use taxonomies that distinguish between groups such as cybercriminals, state-linked actors, ideologically motivated actors, thrill seekers or trolls, insiders, and competitors. Threat actor classifications are used in risk management, cyber threat intelligence, and incident response to connect observed behaviour with possible objectives and likely future activity. The categories are not always mutually exclusive: the same actor may combine criminal, ideological, commercial, or state-linked motivations, and different organisations may use different names for similar actors. == Risk assessment and security management == In risk assessment, threat actor analysis is used to identify who or what may create, carry, transmit, support, or exploit a threat, and how that actor relates to the system being assessed. Rausand and Haugen classify threat actors by their relationship to the system, distinguishing between internal and external actors, and by intent, distinguishing between intentional and unintentional actors. Threat actor classification may also support incident investigation. Rogers argued that actor categories could be inferred from observable case points, such as tools used, messages left, data targeted, forensic knowledge, and the degree of damage, allowing investigators to assess likely motivation and skill level. Later work similarly linked actor classification to operational analysis. Chng, Lu, Kumar and Yau proposed a framework connecting hacker types, motivations and typical strategies, arguing that observed behaviour before or during an attack can help analysts infer the likely type of actor involved. At the strategic level, actor analysis may consider an actor's resources, capabilities, degree of state involvement, motivations and objectives. == Landscape == The United Nations Institute for Disarmament Research has described the contemporary cyberthreat landscape as involving an increasingly diverse and interconnected set of actors, including state-led operations, cybercriminal syndicates, ideological hacktivists, commercial cyber mercenaries, private companies and civilian volunteers. Its 2026 report argued that these actors vary in resources, technical sophistication and relationships with states, making it traditional distinctions between state, civilian combatant roles, and legitimate and illegitimate conduct harder to apply. == Academic taxonomies == Early taxonomies classified hackers by activity, skill, motivation, or criminal profile. Landreth proposed six categories based on activity: novice, student, tourist, crasher, and thief. Hollinger classified computer misuse into pirates, browsers, and crackers, describing a progression from less-skilled activity to more technically serious offences. Chantler used attributes including activity, skill, knowledge, motivation, and duration of involvement to distinguish between an elite group, neophytes, and "losers and lamers". Parker proposed seven profiles of cybercriminals: pranksters, hacksters, malicious hackers, personal problem solvers, career criminals, extreme advocates, and malcontents, addicts, and irrational or incompetent people. In 2000, Marc Rogers proposed a taxonomy of hackers with seven, non-mutually-exclusive categories: newbie/tool kit users, cyber-punks, internals, coders, old guard hackers, professional criminals, and cyber-terrorists. Rausand and Haugen distinguish between internal and external threat actors, and between intentional and unintentional threat actors. Internal actors have some relationship with, access to, or position inside the system or organisation, while external actors operate from outside it. Intentional actors seek to create, exploit, or support a threat event, whereas unintentional actors may cause or enable a threat event through error, negligence, accident, or lack of awareness. Rogers later revised his hacker taxonomy into Novices, Cyber-punks, Internals, Petty Thieves, Virus Writers, Old Guard hackers, Professional Criminals, Information Warriors, and, more tentatively, Political Activists. In the model, motivation is grouped into four broad domains: curiosity, notoriety, revenge, and financial gain. A 2022 review by Chng, Lu, Kumar and Yau examined 11 hacker typologies published over three decades and proposed a unified framework linking hacker types, motivations, and strategies. The framework identified 13 hacker types and seven motivations, and argued that observed strategies during an attack can help analysts infer the likely type of actor involved. == Government taxonomies == Taxonomies of threat actors by governments are much more likely to include state-level threat actors. In the United States the National Institute of Standards and Technology (NIST) uses the term threat source in its risk-assessment guidance: organisations are directed to identify and characterise threat sources of concern, including capability, intent and targeting for adversarial threat sources, and the range of effects for non-adversarial threat sources. NIST treats threat-source identification as part of the risk-assessment process, alongside identifying threat events, vulnerabilities, likelihood and impact. In the EU, European Union Agency for Cybersecurity publishes the annual ENISA Threat Landscape, which analyses cyber incidents and adversary behaviour affecting the European Union. The 2025 report analysed selected incidents from the previous year and grouped activity around cybercrime, state-aligned activity, foreign information manipulation and interference, and hacktivism. In ENISA's 2025 analysis, hacktivist activity dominated reporting, representing almost 80% of recorded incidents and consisting mainly of low-level distributed denial-of-service operations. ENISA also reported increasing convergence between hacktivism, cybercrime and state-nexus activity, including state-aligned use of hacktivist personas, hacktivist adoption of ransomware, and false-flag or impersonation activity. At the UN level, A 2026 report by the United Nations Institute for Disarmament Research described the cyberthreat landscape as involving state-led operations, cybercriminal syndicates, ideological hacktivists, commercial cyber mercenaries, and civilian volunteers, with actors varying in resources, technical sophistication, and links to states. Canada defines threat actors as states, groups, or individuals who aim to cause harm by exploiting a vulnerability with malicious intent. A threat actor must be trying to gain access to information systems to access or alter data, devices, systems, or networks. The Japanese government's National Centre of Incident Readiness and Strategy (NISC) was established in 2015 to create a "free, fair and secure cyberspace" in Japan. The NICS created a cybersecurity strategy in 2018 that outlines nation-states and cybercrime to be some of the most key threats. It also indicates that terrorist usage of the cyberspace needs to be monitored and understood. The Security Council of the Russian Federation published the cyber security strategy doctrine in 2016. This strategy highlights the following threat actors as a risk to cyber security measures: nation-state actors, cyber criminals, and terrorists. == Techniques == Threat actors use techniques like Social engineering (security), and Phishing, alongside technical exploits like Cross-site scripting, SQL injection, and denial-of-service attacks. == Limitations == In practice, actor categories may overlap (Edward Snowden for example), and the same activity may combine features associated with hacktivism, cybercrime and state-linked operations. The lines between hacktivism, cybercrime and state-nexus activity had continued to blur, with shared toolsets, overlapping methods, fake personas, hacktivist adoption of ransomware, and cybercriminal or state-linked actors masquerading as other groups. Threat actor analysis also has limits as a risk-management method. NIST notes that risk assessments depend on their purpose, scope, assumptions, constraints, information sources, risk model and analytic approach, and that assessments are tied to particular time frames and organisational contexts. NIST also warns that simple threat-vulnerability pairing may be undesirable or problematic where there are many threats and vulnerabilities, and recom

  Read more →
• 

  Linear discriminant analysis

  Linear discriminant analysis (LDA), normal discriminant analysis (NDA), canonical variates analysis (CVA), or discriminant function analysis is a generalization of Fisher's linear discriminant, a method used in statistics and other fields, to find a linear combination of features that characterizes or separates two or more classes of objects or events. The resulting combination may be used as a linear classifier, or, more commonly, for dimensionality reduction before later classification. LDA is closely related to analysis of variance (ANOVA) and regression analysis, which also attempt to express one dependent variable as a linear combination of other features or measurements. However, ANOVA uses categorical independent variables and a continuous dependent variable, whereas discriminant analysis has continuous independent variables and a categorical dependent variable (i.e. the class label). Logistic regression and probit regression are more similar to LDA than ANOVA is, as they also explain a categorical variable by the values of continuous independent variables. These other methods are preferable in applications where it is not reasonable to assume that the independent variables have a normal distribution, which is a fundamental assumption of the LDA method. LDA is also closely related to principal component analysis (PCA) and factor analysis in that they both look for linear combinations of variables which best explain the data. LDA explicitly attempts to model the difference between the classes of data. PCA, in contrast, does not take into account any difference in class, and factor analysis builds the feature combinations based on similarities rather than differences. Discriminant analysis is also different from factor analysis in that it is not an interdependence technique: a distinction between independent variables and dependent variables (also called criterion variables) must be made. LDA works when the measurements made on independent variables for each observation are continuous quantities. When dealing with categorical independent variables, the equivalent technique is discriminant correspondence analysis. Discriminant analysis is used when groups are known a priori (unlike in cluster analysis). Each case must have a score on one or more quantitative predictor measures, and a score on a group measure. In simple terms, discriminant function analysis is classification - the act of distributing things into groups, classes or categories of the same type. == History == The original dichotomous discriminant analysis was developed by Sir Ronald Fisher in 1936. It is different from an ANOVA or MANOVA, which is used to predict one (ANOVA) or multiple (MANOVA) continuous dependent variables by one or more independent categorical variables. Discriminant function analysis is useful in determining whether a set of variables is effective in predicting category membership. == LDA for two classes == Consider a set of observations x → {\displaystyle {\vec {x}}} (also called features, attributes, variables or measurements) for each sample of an object or event with known class y {\displaystyle y} . This set of samples is called the training set in a supervised learning context. The classification problem is then to find a good predictor for the class y {\displaystyle y} of any sample of the same distribution (not necessarily from the training set) given only an observation x → {\displaystyle {\vec {x}}} . LDA approaches the problem by assuming that the conditional probability density functions p ( x → | y = 0 ) {\displaystyle p({\vec {x}}|y=0)} and p ( x → | y = 1 ) {\displaystyle p({\vec {x}}|y=1)} are both the normal distribution with mean and covariance parameters ( μ → 0 , Σ 0 ) {\displaystyle \left({\vec {\mu }}_{0},\Sigma _{0}\right)} and ( μ → 1 , Σ 1 ) {\displaystyle \left({\vec {\mu }}_{1},\Sigma _{1}\right)} , respectively. Under this assumption, the Bayes-optimal solution is to predict points as being from the second class if the log of the likelihood ratios is bigger than some threshold T, so that: 1 2 ( x → − μ → 0 ) T Σ 0 − 1 ( x → − μ → 0 ) + 1 2 ln ⁡ | Σ 0 | − 1 2 ( x → − μ → 1 ) T Σ 1 − 1 ( x → − μ → 1 ) − 1 2 ln ⁡ | Σ 1 | > T {\displaystyle {\frac {1}{2}}({\vec {x}}-{\vec {\mu }}_{0})^{\mathrm {T} }\Sigma _{0}^{-1}({\vec {x}}-{\vec {\mu }}_{0})+{\frac {1}{2}}\ln |\Sigma _{0}|-{\frac {1}{2}}({\vec {x}}-{\vec {\mu }}_{1})^{\mathrm {T} }\Sigma _{1}^{-1}({\vec {x}}-{\vec {\mu }}_{1})-{\frac {1}{2}}\ln |\Sigma _{1}|\ >\ T} Without any further assumptions, the resulting classifier is referred to as quadratic discriminant analysis (QDA). LDA instead makes the additional simplifying homoscedasticity assumption (i.e. that the class covariances are identical, so Σ 0 = Σ 1 = Σ {\displaystyle \Sigma _{0}=\Sigma _{1}=\Sigma } ) and that the covariances have full rank. In this case, several terms cancel: x → T Σ 0 − 1 x → = x → T Σ 1 − 1 x → {\displaystyle {\vec {x}}^{\mathrm {T} }\Sigma _{0}^{-1}{\vec {x}}={\vec {x}}^{\mathrm {T} }\Sigma _{1}^{-1}{\vec {x}}} x → T Σ i − 1 μ → i = μ → i T Σ i − 1 x → {\displaystyle {\vec {x}}^{\mathrm {T} }{\Sigma _{i}}^{-1}{\vec {\mu }}_{i}={{\vec {\mu }}_{i}}^{\mathrm {T} }{\Sigma _{i}}^{-1}{\vec {x}}} because both sides are scalar and transpose to each other ( Σ i {\displaystyle \Sigma _{i}} is Hermitian) and the above decision criterion becomes a threshold on the dot product w → T x → > c {\displaystyle {\vec {w}}^{\mathrm {T} }{\vec {x}}>c} for some threshold constant c, where w → = Σ − 1 ( μ → 1 − μ → 0 ) {\displaystyle {\vec {w}}=\Sigma ^{-1}({\vec {\mu }}_{1}-{\vec {\mu }}_{0})} c = 1 2 w → T ( μ → 1 + μ → 0 ) {\displaystyle c={\frac {1}{2}}\,{\vec {w}}^{\mathrm {T} }({\vec {\mu }}_{1}+{\vec {\mu }}_{0})} This means that the criterion of an input x → {\displaystyle {\vec {x}}} being in a class y {\displaystyle y} is purely a function of this linear combination of the known observations. It is often useful to see this conclusion in geometrical terms: the criterion of an input x → {\displaystyle {\vec {x}}} being in a class y {\displaystyle y} is purely a function of projection of multidimensional-space point x → {\displaystyle {\vec {x}}} onto vector w → {\displaystyle {\vec {w}}} (thus, we only consider its direction). In other words, the observation belongs to y {\displaystyle y} if corresponding x → {\displaystyle {\vec {x}}} is located on a certain side of a hyperplane perpendicular to w → {\displaystyle {\vec {w}}} . The location of the plane is defined by the threshold c {\displaystyle c} . == Assumptions == The assumptions of discriminant analysis are the same as those for MANOVA. The analysis is quite sensitive to outliers and the size of the smallest group must be larger than the number of predictor variables. Multivariate normality: Independent variables are normal for each level of the grouping variable. Homogeneity of variance/covariance (homoscedasticity): Variances among group variables are the same across levels of predictors. Can be tested with Box's M statistic. It has been suggested, however, that linear discriminant analysis be used when covariances are equal, and that quadratic discriminant analysis may be used when covariances are not equal. Independence: Participants are assumed to be randomly sampled, and a participant's score on one variable is assumed to be independent of scores on that variable for all other participants. It has been suggested that discriminant analysis is relatively robust to slight violations of these assumptions, and it has also been shown that discriminant analysis may still be reliable when using dichotomous variables (where multivariate normality is often violated). == Discriminant functions == Discriminant analysis works by creating one or more linear combinations of predictors, creating a new latent variable for each function. These functions are called discriminant functions. The number of functions possible is either N g − 1 {\displaystyle N_{g}-1} where N g {\displaystyle N_{g}} = number of groups, or p {\displaystyle p} (the number of predictors), whichever is smaller. The first function created maximizes the differences between groups on that function. The second function maximizes differences on that function, but also must not be correlated with the previous function. This continues with subsequent functions with the requirement that the new function not be correlated with any of the previous functions. Given group j {\displaystyle j} , with R j {\displaystyle \mathbb {R} _{j}} sets of sample space, there is a discriminant rule such that if x ∈ R j {\displaystyle x\in \mathbb {R} _{j}} , then x ∈ j {\displaystyle x\in j} . Discriminant analysis then, finds “good” regions of R j {\displaystyle \mathbb {R} _{j}} to minimize classification error, therefore leading to a high percent correct classified in the classification table. Each function is given a discriminant score to determine how well it predicts group placement. Structure Corr

  Read more →
• 

  Radial basis function kernel

  In machine learning, the radial basis function kernel, or RBF kernel, is a popular kernel function used in various kernelized learning algorithms. In particular, it is commonly used in support vector machine classification. The RBF kernel on two samples x , x ′ ∈ R k {\displaystyle \mathbf {x} ,\mathbf {x'} \in \mathbb {R} ^{k}} , represented as feature vectors in some input space, is defined as K ( x , x ′ ) = exp ⁡ ( − ‖ x − x ′ ‖ 2 2 σ 2 ) {\displaystyle K(\mathbf {x} ,\mathbf {x'} )=\exp \left(-{\frac {\|\mathbf {x} -\mathbf {x'} \|^{2}}{2\sigma ^{2}}}\right)} ‖ x − x ′ ‖ 2 {\displaystyle \textstyle \|\mathbf {x} -\mathbf {x'} \|^{2}} may be recognized as the squared Euclidean distance between the two feature vectors. σ {\displaystyle \sigma } is a free parameter. An equivalent definition involves a parameter γ = 1 2 σ 2 {\displaystyle \textstyle \gamma ={\tfrac {1}{2\sigma ^{2}}}} : K ( x , x ′ ) = exp ⁡ ( − γ ‖ x − x ′ ‖ 2 ) {\displaystyle K(\mathbf {x} ,\mathbf {x'} )=\exp(-\gamma \|\mathbf {x} -\mathbf {x'} \|^{2})} Since the value of the RBF kernel decreases with distance and ranges between zero (in the infinite-distance limit) and one (when x = x'), it has a ready interpretation as a similarity measure. The feature space of the kernel has an infinite number of dimensions; for σ = 1 {\displaystyle \sigma =1} , its expansion using the multinomial theorem is: exp ⁡ ( − 1 2 ‖ x − x ′ ‖ 2 ) = exp ⁡ ( 2 2 x ⊤ x ′ − 1 2 ‖ x ‖ 2 − 1 2 ‖ x ′ ‖ 2 ) = exp ⁡ ( x ⊤ x ′ ) exp ⁡ ( − 1 2 ‖ x ‖ 2 ) exp ⁡ ( − 1 2 ‖ x ′ ‖ 2 ) = ∑ j = 0 ∞ ( x ⊤ x ′ ) j j ! exp ⁡ ( − 1 2 ‖ x ‖ 2 ) exp ⁡ ( − 1 2 ‖ x ′ ‖ 2 ) = ∑ j = 0 ∞ ∑ n 1 + n 2 + ⋯ + n k = j exp ⁡ ( − 1 2 ‖ x ‖ 2 ) x 1 n 1 ⋯ x k n k n 1 ! ⋯ n k ! exp ⁡ ( − 1 2 ‖ x ′ ‖ 2 ) x ′ 1 n 1 ⋯ x ′ k n k n 1 ! ⋯ n k ! = ⟨ φ ( x ) , φ ( x ′ ) ⟩ {\displaystyle {\begin{alignedat}{2}\exp \left(-{\frac {1}{2}}\|\mathbf {x} -\mathbf {x'} \|^{2}\right)&=\exp \left({\frac {2}{2}}\mathbf {x} ^{\top }\mathbf {x'} -{\frac {1}{2}}\|\mathbf {x} \|^{2}-{\frac {1}{2}}\|\mathbf {x'} \|^{2}\right)\\[5pt]&=\exp \left(\mathbf {x} ^{\top }\mathbf {x'} \right)\exp \left(-{\frac {1}{2}}\|\mathbf {x} \|^{2}\right)\exp \left(-{\frac {1}{2}}\|\mathbf {x'} \|^{2}\right)\\[5pt]&=\sum _{j=0}^{\infty }{\frac {(\mathbf {x} ^{\top }\mathbf {x'} )^{j}}{j!}}\exp \left(-{\frac {1}{2}}\|\mathbf {x} \|^{2}\right)\exp \left(-{\frac {1}{2}}\|\mathbf {x'} \|^{2}\right)\\[5pt]&=\sum _{j=0}^{\infty }\quad \sum _{n_{1}+n_{2}+\dots +n_{k}=j}\exp \left(-{\frac {1}{2}}\|\mathbf {x} \|^{2}\right){\frac {x_{1}^{n_{1}}\cdots x_{k}^{n_{k}}}{\sqrt {n_{1}!\cdots n_{k}!}}}\exp \left(-{\frac {1}{2}}\|\mathbf {x'} \|^{2}\right){\frac {{x'}_{1}^{n_{1}}\cdots {x'}_{k}^{n_{k}}}{\sqrt {n_{1}!\cdots n_{k}!}}}\\[5pt]&=\langle \varphi (\mathbf {x} ),\varphi (\mathbf {x'} )\rangle \end{alignedat}}} φ ( x ) = exp ⁡ ( − 1 2 ‖ x ‖ 2 ) ( a ℓ 0 ( 0 ) , a 1 ( 1 ) , … , a ℓ 1 ( 1 ) , … , a 1 ( j ) , … , a ℓ j ( j ) , … ) {\displaystyle \varphi (\mathbf {x} )=\exp \left(-{\frac {1}{2}}\|\mathbf {x} \|^{2}\right)\left(a_{\ell _{0}}^{(0)},a_{1}^{(1)},\dots ,a_{\ell _{1}}^{(1)},\dots ,a_{1}^{(j)},\dots ,a_{\ell _{j}}^{(j)},\dots \right)} where ℓ j = ( k + j − 1 j ) {\displaystyle \ell _{j}={\tbinom {k+j-1}{j}}} , a ℓ ( j ) = x 1 n 1 ⋯ x k n k n 1 ! ⋯ n k ! | n 1 + n 2 + ⋯ + n k = j ∧ 1 ≤ ℓ ≤ ℓ j {\displaystyle a_{\ell }^{(j)}={\frac {x_{1}^{n_{1}}\cdots x_{k}^{n_{k}}}{\sqrt {n_{1}!\cdots n_{k}!}}}\quad |\quad n_{1}+n_{2}+\dots +n_{k}=j\wedge 1\leq \ell \leq \ell _{j}} == Approximations == Because support vector machines and other models employing the kernel trick do not scale well to large numbers of training samples or large numbers of features in the input space, several approximations to the RBF kernel (and similar kernels) have been introduced. Typically, these take the form of a function z that maps a single vector to a vector of higher dimensionality, approximating the kernel: ⟨ z ( x ) , z ( x ′ ) ⟩ ≈ ⟨ φ ( x ) , φ ( x ′ ) ⟩ = K ( x , x ′ ) {\displaystyle \langle z(\mathbf {x} ),z(\mathbf {x'} )\rangle \approx \langle \varphi (\mathbf {x} ),\varphi (\mathbf {x'} )\rangle =K(\mathbf {x} ,\mathbf {x'} )} where φ {\displaystyle \textstyle \varphi } is the implicit mapping embedded in the RBF kernel. === Fourier random features === One way to construct such a z is to randomly sample from the Fourier transformation of the kernel φ ( x ) = 1 D [ cos ⁡ ⟨ w 1 , x ⟩ , sin ⁡ ⟨ w 1 , x ⟩ , … , cos ⁡ ⟨ w D , x ⟩ , sin ⁡ ⟨ w D , x ⟩ ] T {\displaystyle \varphi (x)={\frac {1}{\sqrt {D}}}[\cos \langle w_{1},x\rangle ,\sin \langle w_{1},x\rangle ,\ldots ,\cos \langle w_{D},x\rangle ,\sin \langle w_{D},x\rangle ]^{T}} where w 1 , . . . , w D {\displaystyle w_{1},...,w_{D}} are independent samples from the normal distribution N ( 0 , σ − 2 I ) {\displaystyle N(0,\sigma ^{-2}I)} . Theorem: E ⁡ [ ⟨ φ ( x ) , φ ( y ) ⟩ ] = e ‖ x − y ‖ 2 / ( 2 σ 2 ) . {\displaystyle \operatorname {E} [\langle \varphi (x),\varphi (y)\rangle ]=e^{\|x-y\|^{2}/(2\sigma ^{2})}.} Proof: It suffices to prove the case of D = 1 {\displaystyle D=1} . Use the trigonometric identity cos ⁡ ( a − b ) = cos ⁡ ( a ) cos ⁡ ( b ) + sin ⁡ ( a ) sin ⁡ ( b ) {\displaystyle \cos(a-b)=\cos(a)\cos(b)+\sin(a)\sin(b)} , the spherical symmetry of Gaussian distribution, then evaluate the integral ∫ − ∞ ∞ cos ⁡ ( k x ) e − x 2 / 2 2 π d x = e − k 2 / 2 . {\displaystyle \int _{-\infty }^{\infty }{\frac {\cos(kx)e^{-x^{2}/2}}{\sqrt {2\pi }}}dx=e^{-k^{2}/2}.} Theorem: Var ⁡ [ ⟨ φ ( x ) , φ ( y ) ⟩ ] = O ( D − 1 ) {\displaystyle \operatorname {Var} [\langle \varphi (x),\varphi (y)\rangle ]=O(D^{-1})} . (Appendix A.2). === Nyström method === Another approach uses the Nyström method to approximate the eigendecomposition of the Gram matrix K, using only a random sample of the training set.

  Read more →
• 

  IDistance

  In pattern recognition, iDistance is an indexing and query processing technique for k-nearest neighbor queries on point data in multi-dimensional metric spaces. The kNN query is one of the hardest problems on multi-dimensional data, especially when the dimensionality of the data is high. iDistance is designed to process kNN queries in high-dimensional spaces efficiently and performs extremely well for skewed data distributions, which usually occur in real-life data sets. iDistance employs a two-phase search strategy involving an initial filtering of candidate regions and a subsequent refinement of results, an approach aligned with the Filter and Refine Principle (FRP). This means that the index first prunes the search space to eliminate unlikely candidates, then verifies the true nearest neighbors in a refinement step, following the general FRP paradigm used in database search algorithms. The iDistance index can also be augmented with machine learning models to learn data distributions for improved searching and storage of multi-dimensional data. == Indexing == Building the iDistance index has two steps: A number of reference points in the data space are chosen. There are various ways of choosing reference points. Using cluster centers as reference points is the most efficient way. The data points are partitioned into Voronoi cells based on well-chosen reference points. The distance between a data point and its closest reference point is calculated. This distance plus a scaling value is called the point's iDistance. By this means, points in a multi-dimensional space are mapped to one-dimensional values, and then a B+-tree can be adopted to index the points using the iDistance as the key. The figure on the right shows an example where three reference points (O1, O2, O3) are chosen. The data points are then mapped to a one-dimensional space and indexed in a B+-tree. Various extensions have been proposed to make the selection of reference points for effective query performance, including employing machine learning to learn the identification of reference points. == Query processing == To process a kNN query, the query is mapped to a number of one-dimensional range queries, which can be processed efficiently on a B+-tree. In the above figure, the query Q is mapped to a value in the B+-tree while the kNN search ``sphere" is mapped to a range in the B+-tree. The search sphere expands gradually until the k NNs are found. This corresponds to gradually expanding range searches in the B+-tree. The iDistance technique can be viewed as a way of accelerating the sequential scan. Instead of scanning records from the beginning to the end of the data file, the iDistance starts the scan from spots where the nearest neighbors can be obtained early with a very high probability. == Applications == The iDistance has been used in many applications including Image retrieval Video indexing Similarity search in P2P systems Mobile computing Recommender system == Historical background == The iDistance was first proposed by Cui Yu, Beng Chin Ooi, Kian-Lee Tan and H. V. Jagadish in 2001. Later, together with Rui Zhang, they improved the technique and performed a more comprehensive study on it in 2005.

  Read more →
• 

  Douglas Parkhill

  Douglas F. Parkhill is a Canadian technologist and former research minister, best known for his pioneering work on what is now called cloud computing, and his work on Canada's Telidon videotex project. He started working at the Canadian ministry of Communications (now part of the Department of Trade and Industry) in 1969, having previously worked at the Mitre Corporation. He was responsible for many activities in communications satellites, computer communications, command and control systems and telecommunications. He was winner of the Treasury Board of Canada Secretariat's Outstanding Achievement award in 1982, the Conestoga shield for services to government and industry in computer communications research and development, the Touche Ross award for Telidon development. He was an author of several publications including the 1966 book, The Challenge of the Computer Utility. In the book, Parkhill thoroughly explored many of the modern-day characteristics of cloud computing (elastic provisioning through a utility service) as well as the comparison to the electricity industry and the use of public, private, government and community forms. The book won the McKinsey Foundation award for distinguished contributions to management literature. He worked with Dave Godfrey, the Canadian writer and novelist on a later book Gutenberg two about the social and political meaning of computer technology. He was in charge of research at the Federal Department of Communications at the time when the department was funding development of the Telidon videotext system, was heavily involved in promoting the system, and had overall control of the program. In a radio broadcast in 1980, he outlined some of the potential of the system, from financial information, to theatre reservations, with the ability to pay and print out tickets from the system. He later documented the history of the Telidon project, and the history of videotext in general. == Publications == The Challenge of the Computer Utility, Addison-Wesley, 1966, ISBN 0-201-05720-4 edited with Dave Godfrey, Gutenberg Two: The New Electronics and Social Change, Press Porcepic, 1979, ISBN 0-88878-191-1 The Beginning of a Beginning. Ottawa; Department of Communications, 1987. A history of the Telidon project.

  Read more →
• 

  Self-play

  Self-play is a technique for improving the performance of reinforcement learning agents. Intuitively, agents learn to improve their performance by playing "against themselves". == Definition and motivation == In multi-agent reinforcement learning experiments, researchers try to optimize the performance of a learning agent on a given task, in cooperation or competition with one or more agents. These agents learn by trial-and-error, and researchers may choose to have the learning algorithm play the role of two or more of the different agents. When successfully executed, this technique has a double advantage: It provides a straightforward way to determine the actions of the other agents, resulting in a meaningful challenge. It increases the amount of experience that can be used to improve the policy, by a factor of two or more, since the viewpoints of each of the different agents can be used for learning. Czarnecki et al argue that most of the games that people play for fun are "Games of Skill", meaning games whose space of all possible strategies looks like a spinning top. In more detail, we can partition the space of strategies into sets L 1 , L 2 , . . . , L n {\displaystyle L_{1},L_{2},...,L_{n}} , such that any i < j , π i ∈ L i , π j ∈ L j {\displaystyle i Read more →

• 

  Dynamic Bayesian network

  A dynamic Bayesian network (DBN) is a Bayesian network (BN) which relates variables to each other over adjacent time steps. == History == A dynamic Bayesian network (DBN) is often called a "two-timeslice" BN (2TBN) because it says that at any point in time T, the value of a variable can be calculated from the internal regressors and the immediate prior value (time T-1). DBNs were developed by Paul Dagum in the early 1990s at Stanford University's Section on Medical Informatics. Dagum developed DBNs to unify and extend traditional linear state-space models such as Kalman filters, linear and normal forecasting models such as ARMA and simple dependency models such as hidden Markov models into a general probabilistic representation and inference mechanism for arbitrary nonlinear and non-normal time-dependent domains. Today, DBNs are common in robotics, and have shown potential for a wide range of data mining applications. For example, they have been used in speech recognition, digital forensics, protein sequencing, and bioinformatics. DBN is a generalization of hidden Markov models and Kalman filters. DBNs are conceptually related to probabilistic Boolean networks and can, similarly, be used to model dynamical systems at steady-state.

  Read more →
• 

  Modern Hopfield network

  Modern Hopfield networks (also known as Dense Associative Memories) are generalizations of the classical Hopfield networks that break the linear scaling relationship between the number of input features and the number of stored memories. This is achieved by introducing stronger non-linearities (either in the energy function or neurons’ activation functions) leading to super-linear (even an exponential) memory storage capacity as a function of the number of feature neurons. The network still requires a sufficient number of hidden neurons. The key theoretical idea behind the modern Hopfield networks is to use an energy function and an update rule that is more sharply peaked around the stored memories in the space of neuron’s configurations compared to the classical Hopfield network. == Classical Hopfield networks == Hopfield networks are recurrent neural networks with dynamical trajectories converging to fixed point attractor states and described by an energy function. The state of each model neuron i {\textstyle i} is defined by a time-dependent variable V i {\displaystyle V_{i}} , which can be chosen to be either discrete or continuous. A complete model describes the mathematics of how the future state of activity of each neuron depends on the known present or previous activity of all the neurons. In the original Hopfield model of associative memory, the variables were binary, and the dynamics were described by a one-at-a-time update of the state of the neurons. An energy function quadratic in the V i {\displaystyle V_{i}} was defined, and the dynamics consisted of changing the activity of each single neuron i {\displaystyle i} only if doing so would lower the total energy of the system. This same idea was extended to the case of V i {\displaystyle V_{i}} being a continuous variable representing the output of neuron i {\displaystyle i} , and V i {\displaystyle V_{i}} being a monotonic function of an input current. The dynamics became expressed as a set of first-order differential equations for which the "energy" of the system always decreased. The energy in the continuous case has one term which is quadratic in the V i {\displaystyle V_{i}} (as in the binary model), and a second term which depends on the gain function (neuron's activation function). While having many desirable properties of associative memory, both of these classical systems suffer from a small memory storage capacity, which scales linearly with the number of input features. == Discrete variables == A simple example of the Modern Hopfield network can be written in terms of binary variables V i {\displaystyle V_{i}} that represent the active V i = + 1 {\displaystyle V_{i}=+1} and inactive V i = − 1 {\displaystyle V_{i}=-1} state of the model neuron i {\displaystyle i} . E = − ∑ μ = 1 N mem F ( ∑ i = 1 N f ξ μ i V i ) {\displaystyle E=-\sum \limits _{\mu =1}^{N_{\text{mem}}}F{\Big (}\sum \limits _{i=1}^{N_{f}}\xi _{\mu i}V_{i}{\Big )}} In this formula the weights ξ μ i {\textstyle \xi _{\mu i}} represent the matrix of memory vectors (index μ = 1... N mem {\displaystyle \mu =1...N_{\text{mem}}} enumerates different memories, and index i = 1... N f {\displaystyle i=1...N_{f}} enumerates the content of each memory corresponding to the i {\displaystyle i} -th feature neuron), and the function F ( x ) {\displaystyle F(x)} is a rapidly growing non-linear function. The update rule for individual neurons (in the asynchronous case) can be written in the following form V i ( t + 1 ) = sign ⁡ [ ∑ μ = 1 N mem ( F ( ξ μ i + ∑ j ≠ i ξ μ j V j ( t ) ) − F ( − ξ μ i + ∑ j ≠ i ξ μ j V j ( t ) ) ) ] {\displaystyle V_{i}^{(t+1)}=\operatorname {sign} {\bigg [}\sum \limits _{\mu =1}^{N_{\text{mem}}}{\bigg (}F{\Big (}\xi _{\mu i}+\sum \limits _{j\neq i}\xi _{\mu j}V_{j}^{(t)}{\Big )}-F{\Big (}-\xi _{\mu i}+\sum \limits _{j\neq i}\xi _{\mu j}V_{j}^{(t)}{\Big )}{\bigg )}{\bigg ]}} which states that in order to calculate the updated state of the i {\textstyle i} -th neuron the network compares two energies: the energy of the network with the i {\displaystyle i} -th neuron in the ON state and the energy of the network with the i {\displaystyle i} -th neuron in the OFF state, given the states of the remaining neuron. The updated state of the i {\displaystyle i} -th neuron selects the state that has the lowest of the two energies. In the limiting case when the non-linear energy function is quadratic F ( x ) = x 2 {\displaystyle F(x)=x^{2}} these equations reduce to the familiar energy function and the update rule for the classical binary Hopfield network. The memory storage capacity of these networks can be calculated for random binary patterns. For the power energy function F ( x ) = x n {\displaystyle F(x)=x^{n}} the maximal number of memories that can be stored and retrieved from this network without errors is given by N mem max ≈ 1 2 ( 2 n − 3 ) ! ! N f n − 1 ln ⁡ ( N f ) {\displaystyle N_{\text{mem}}^{\max }\approx {\frac {1}{2(2n-3)!!}}{\frac {N_{f}^{n-1}}{\ln(N_{f})}}} For an exponential energy function F ( x ) = e x {\textstyle F(x)=e^{x}} the memory storage capacity is exponential in the number of feature neurons N mem max ≈ 2 N f / 2 {\displaystyle N_{\text{mem}}^{\max }\approx 2^{N_{f}/2}} == Continuous variables == Modern Hopfield networks or Dense Associative Memories can be best understood in continuous variables and continuous time. Consider the network architecture, shown in Fig.1, and the equations for the neurons' state evolutionwhere the currents of the feature neurons are denoted by x i {\textstyle x_{i}} , and the currents of the memory neurons are denoted by h μ {\displaystyle h_{\mu }} ( h {\displaystyle h} stands for hidden neurons). There are no synaptic connections among the feature neurons or the memory neurons. A matrix ξ μ i {\displaystyle \xi _{\mu i}} denotes the strength of synapses from a feature neuron i {\displaystyle i} to the memory neuron μ {\displaystyle \mu } . The synapses are assumed to be symmetric, so that the same value characterizes a different physical synapse from the memory neuron μ {\displaystyle \mu } to the feature neuron i {\displaystyle i} . The outputs of the memory neurons and the feature neurons are denoted by f μ {\displaystyle f_{\mu }} and g i {\displaystyle g_{i}} , which are non-linear functions of the corresponding currents. In general these outputs can depend on the currents of all the neurons in that layer so that f μ = f ( { h μ } ) {\displaystyle f_{\mu }=f(\{h_{\mu }\})} and g i = g ( { x i } ) {\textstyle g_{i}=g(\{x_{i}\})} . It is convenient to define these activation function as derivatives of the Lagrangian functions for the two groups of neuronsThis way the specific form of the equations for neuron's states is completely defined once the Lagrangian functions are specified. Finally, the time constants for the two groups of neurons are denoted by τ f {\displaystyle \tau _{f}} and τ h {\displaystyle \tau _{h}} , I i {\displaystyle I_{i}} is the input current to the network that can be driven by the presented data. General systems of non-linear differential equations can have many complicated behaviors that can depend on the choice of the non-linearities and the initial conditions. For Hopfield networks, however, this is not the case - the dynamical trajectories always converge to a fixed point attractor state. This property is achieved because these equations are specifically engineered so that they have an underlying energy function The terms grouped into square brackets represent a Legendre transform of the Lagrangian function with respect to the states of the neurons. If the Hessian matrices of the Lagrangian functions are positive semi-definite, the energy function is guaranteed to decrease on the dynamical trajectory This property makes it possible to prove that the system of dynamical equations describing temporal evolution of neurons' activities will eventually reach a fixed point attractor state. In certain situations one can assume that the dynamics of hidden neurons equilibrates at a much faster time scale compared to the feature neurons, τ h ≪ τ f {\textstyle \tau _{h}\ll \tau _{f}} . In this case the steady state solution of the second equation in the system (1) can be used to express the currents of the hidden units through the outputs of the feature neurons. This makes it possible to reduce the general theory (1) to an effective theory for feature neurons only. The resulting effective update rules and the energies for various common choices of the Lagrangian functions are shown in Fig.2. In the case of log-sum-exponential Lagrangian function the update rule (if applied once) for the states of the feature neurons is the attention mechanism commonly used in many modern AI systems (see Ref. for the derivation of this result from the continuous time formulation). == Relationship to classical Hopfield network with continuous variables == Classical formulation of continuous Hopfield networks can be understood as a

  Read more →
• 

  Joseph Stanislaus Ostoja-Kotkowski

  Joseph Stanislaus Ostoja-Kotkowski AM, FRSA (also known as J. S. Ostoja-Kotkowski, Ostoja and Stan Ostoja-Kotkowski; 28 December 1922 – 2 April 1994) was best known for his ground-breaking work in chromasonics, laser kinetics and 'sound and image' productions. He earned recognition in Australia and overseas for his pioneering work in laser sound and image technology. His work included painting (instrumental in developing geometric art in Australia), photography, film-making, theatre design, fabric design, murals, kinetic and static sculpture, stained glass, vitreous enamel murals, op-collages, computer graphics, and laser art. Ostoja flourished between 1940 and 1994. Ostoja's films are still being exhibited. == Biography == Joseph Stanislaus Ostoja-Kotkowski was born in Golub, Poland, on 28 December 1922, descending from an old noble family that was part of the Clan of Ostoja. He studied drawing under Olgierd Vetesco in Przasnysz from 1940-1945. After winning a scholarship, he completed his studies at the Düsseldorf Academy of Fine Arts in Germany in 1949. In 1950 Ostoja migrated to Australia, arriving in Melbourne where he supported himself with work as a labourer. He enrolled at the Victorian School of Fine Arts National Gallery School under Alan Sumner and William Dargie 1950-1955 and there introduced the new abstract expression of Europe both to lecturers and students. He settled in the Adelaide Hills, South Australia, on the Booth estate at Stirling, living under the patronage of the Booth family for over 40 years (Freya Booth, the wife of Edward Stirling Booth, was a daughter of the artist Sir Hans Heysen). His first one-man exhibition was also in South Australia at the Royal Society of Arts, Adelaide. In 1956 Ostoja met and collaborated with Ian Davidson in the production of the short film Five South Australian Artists, and became involved in stage and theatre set design. He co-produced several experimental films again with Ian Davidson, including The Quest of Time in 1957 Ostoja's work in abstract expression began to receive accolades. He won the Cornell Prize for the canvas Form in Landscape. He started to design sets for theatre and dance including for Six Characters in Search of an Author by Luigi Pirandello (1957); the South Australian production of Samuel Beckett's Waiting for Godot (1958); Gaetano Donizetti's Elixir of Love, with novel light settings and modulations, for the Elder Conservatorium of the University of Adelaide which used his techniques for their Opera Workshops (1959); for The Egg; and for two performances of the South Australian Ballet Theatre with light/colour abstract presentations (1959). 1960 This year he designed sets for a new opera group which would eventually grow into the South Australian Opera Company. Among other theatrical events, he designed and executed the scenery for Moon on a Rainbow Shawl by Errol John, and The Teahouse of the August Moon by John Patrick, (a production by the University of Adelaide Theatre Guild). He received artistic satisfaction but little financial reward for these efforts. In this year also, he staged a visual production on the theme of Orpheus, using dance, music and voice with several projectors. This was the first attempt at quadraphonic sound in Australia, working in collaboration with Derek Jolly, who provided the sound and projection equipment. It was also the first demonstration of "Chromasonics" - the science of translating sound into visual images. Ostoja then designed innovative "abstracted" scenery for a production of The Marriage of Figaro and Benjamin Britten's The Turn of the Screw. 1961 Ostoja designed the sets for the controversial South Australian production of Patrick White's The Ham Funeral - also Alan Seymour's Swamp Creatures, both performed by the University of Adelaide Theatre Guild. He designed and constructed six stained glass windows for the Refectory at the University of Adelaide. In this period Ostoja designed special lights and gauzes for difficult effects required in an ambitious production of the opera Don Carlos by the Opera Workshop, for the Elder Conservatorium. 1962 Ostoja designed and built sets for the production of J.B, by Archibald MacLeish, for the second Adelaide Festival of Arts. He exhibited vitreous enamel works in Melbourne's Argus Gallery. Max Harris, in The Bulletin of 20 October 1962, praised Ostoja's sets for My Cousin from Fiji in Union Theatre, Adelaide, and his technique of rear screen projections as later adopted throughout Australia. 1963 Ostoja continued to develop Multi-Image projections, demonstrating for the first time in Australia the concept later to be known as 'audio-visuals!'. Ostoja gave Sir Herbert Read, the art critic, a personal viewing of one of his visual presentations. At Christmas, in the Elder Conservatorium, collaborating again with Derek Jolly, Ostoja gave what was probably the world's first "visual concert", using special projectors and incorporating music, colours and shapes. 1964 With fellow Adelaide artist John Dallwitz, Ostoja co-designed the first of several experimental dance and stage productions in the Adelaide Festival of Arts Sound and Image. The production featured Adelaide dancer Elizabeth_Cameron_Dalman. Also for the Adelaide Festival of Arts of that year, he designed the largest light mosaic ever staged up to that time, upon the facade of an 11-storey building. Ostoja was invited to New Zealand, and exhibited the first electronically generated images in Australia in Melbourne, at the Argus Gallery. His design for the 50-foot (15 m) bas-relief mural for the new B.P. building in Melbourne was the subject of a film which won the "Blue Ribbon" Award in the American Film Festival in New York. 1965 Ostoja designed and made the first light kinetic mural in Australia, and continued to evolve theatrical works using multi-screen and Multi-projector techniques. The Production of Jean Genet's The Balcony was very controversial. With Elizabeth Dalman, Ostoja produced new dance forms for Melbourne Television. He introduced Op Art to Australia, both at South Yarra Gallery in Melbourne, and Gallery A in Sydney. 1966 With John Dallwitz, Ostoja was invited by the Adelaide Festival of Arts to present more experimental theatre, Sound and image 1966. This highly acclaimed production incorporated Australian poetry into the sound, electronic music, and visual images and featured the dancer Antonio Rodrigues. The architect Robin Boyd commissioned Ostoja to design two large Op murals for the Australian Pavilion entrance at the Expo 67. Ostoja was awarded a Churchill Fellowship, which enabled him to have extensive world travel, comparing art and technology in many countries. He began to work with language, contemporary poetry and prose, and computers. 1967 John Dallwitz and Ostoja presented Sound and Image at the Festival of Perth. In Berne, Switzerland, Ostoja received the "Excellence F.I.A.P." Award for innovative photography. 1968 At the Adelaide Festival of Arts, Ostoja and John Dallwitz collaborated again to stage Sound and Image. This was the first theatre production in the world to use a laser beam. It also included the first science fiction play (The Veldt by Ray Bradbury) performed in Australia. Ostoja's theatre methods were increasingly attracting the attention of critics to how plays were staged. "Chromasonics", developed and introduced by Ostoja, was now being used extensively in the entertainment industry. 1969 Ostoja staged Krzysztof Penderecki's St. Luke Passion, a controversial, contemporary religious work. The South Australian The Advertiser wrote an extensive critique of Ostoja's work. Robin Boyd commissioned Ostoja to build a "Chromasonic" exhibit located in the Space Tube at the Australian Pavilion for Expo '70 in Osaka. 1970 Ostoja presented an Australian Aboriginal Dreamtime theme in his "Sound and Image" theatre, working with leading contemporary figures in poetry, music and dance. This was the first production of its kind in Australia, and appeared after the Festival in Melbourne, Sydney, Canberra and Perth. Ostoja's Space Scape mural, sixty feet long by ten feet high, won the Australia-wide competition for a mural for Adelaide Airport. His 120 feet (37 m) high 'light and sound' structure for the Adelaide Festival was the first of its kind in the world. 1971 Ostoja awarded a Creative Arts Fellowship at the Australian National University, Canberra. His 18-month stay resulted in the design and building of a "Chromasonics unit-laser", a 100 feet (30 m) Chromasonic tower, and a world premiere of a Synchronos concert. 1972 With Don Burrows and Don Banks, Ostoja presented Synchronos 72, where one could "hear the colours and see the sounds". Ostoja added Cymatics, developed during the Fellowship, to his workshop repertoire. He was invited to exhibit his photography in the National Gallery, Melbourne. 1973 Ostoja received a Fellowship from the Australian American Education Associatio

  Read more →
• 

  Modes of variation

  In statistics, modes of variation are a continuously indexed set of vectors or functions that are centered at a mean and are used to depict the variation in a population or sample. Typically, variation patterns in the data can be decomposed in descending order of eigenvalues with the directions represented by the corresponding eigenvectors or eigenfunctions. Modes of variation provide a visualization of this decomposition and an efficient description of variation around the mean. Both in principal component analysis (PCA) and in functional principal component analysis (FPCA), modes of variation play an important role in visualizing and describing the variation in the data contributed by each eigencomponent. In real-world applications, the eigencomponents and associated modes of variation aid to interpret complex data, especially in exploratory data analysis (EDA). == Formulation == Modes of variation are a natural extension of PCA and FPCA. === Modes of variation in PCA === If a random vector X = ( X 1 , X 2 , ⋯ , X p ) T {\displaystyle \mathbf {X} =(X_{1},X_{2},\cdots ,X_{p})^{T}} has the mean vector μ p {\displaystyle {\boldsymbol {\mu }}_{p}} , and the covariance matrix Σ p × p {\displaystyle \mathbf {\Sigma } _{p\times p}} with eigenvalues λ 1 ≥ λ 2 ≥ ⋯ ≥ λ p ≥ 0 {\displaystyle \lambda _{1}\geq \lambda _{2}\geq \cdots \geq \lambda _{p}\geq 0} and corresponding orthonormal eigenvectors e 1 , e 2 , ⋯ , e p {\displaystyle \mathbf {e} _{1},\mathbf {e} _{2},\cdots ,\mathbf {e} _{p}} , by eigendecomposition of a real symmetric matrix, the covariance matrix Σ {\displaystyle \mathbf {\Sigma } } can be decomposed as Σ = Q Λ Q T , {\displaystyle \mathbf {\Sigma } =\mathbf {Q} \mathbf {\Lambda } \mathbf {Q} ^{T},} where Q {\displaystyle \mathbf {Q} } is an orthogonal matrix whose columns are the eigenvectors of Σ {\displaystyle \mathbf {\Sigma } } , and Λ {\displaystyle \mathbf {\Lambda } } is a diagonal matrix whose entries are the eigenvalues of Σ {\displaystyle \mathbf {\Sigma } } . By the Karhunen–Loève expansion for random vectors, one can express the centered random vector in the eigenbasis X − μ = ∑ k = 1 p ξ k e k , {\displaystyle \mathbf {X} -{\boldsymbol {\mu }}=\sum _{k=1}^{p}\xi _{k}\mathbf {e} _{k},} where ξ k = e k T ( X − μ ) {\displaystyle \xi _{k}=\mathbf {e} _{k}^{T}(\mathbf {X} -{\boldsymbol {\mu }})} is the principal component associated with the k {\displaystyle k} -th eigenvector e k {\displaystyle \mathbf {e} _{k}} , with the properties E ⁡ ( ξ k ) = 0 , Var ⁡ ( ξ k ) = λ k , {\displaystyle \operatorname {E} (\xi _{k})=0,\operatorname {Var} (\xi _{k})=\lambda _{k},} and E ⁡ ( ξ k ξ l ) = 0 for l ≠ k . {\displaystyle \operatorname {E} (\xi _{k}\xi _{l})=0\ {\text{for}}\ l\neq k.} Then the k {\displaystyle k} -th mode of variation of X {\displaystyle \mathbf {X} } is the set of vectors, indexed by α {\displaystyle \alpha } , m k , α = μ ± α λ k e k , α ∈ [ − A , A ] , {\displaystyle \mathbf {m} _{k,\alpha }={\boldsymbol {\mu }}\pm \alpha {\sqrt {\lambda _{k}}}\mathbf {e} _{k},\alpha \in [-A,A],} where A {\displaystyle A} is typically selected as 2 or 3 {\displaystyle 2\ {\text{or}}\ 3} . === Modes of variation in FPCA === For a square-integrable random function X ( t ) , t ∈ T ⊂ R p {\displaystyle X(t),t\in {\mathcal {T}}\subset R^{p}} , where typically p = 1 {\displaystyle p=1} and T {\displaystyle {\mathcal {T}}} is an interval, denote the mean function by μ ( t ) = E ⁡ ( X ( t ) ) {\displaystyle \mu (t)=\operatorname {E} (X(t))} , and the covariance function by G ( s , t ) = Cov ⁡ ( X ( s ) , X ( t ) ) = ∑ k = 1 ∞ λ k φ k ( s ) φ k ( t ) , {\displaystyle G(s,t)=\operatorname {Cov} (X(s),X(t))=\sum _{k=1}^{\infty }\lambda _{k}\varphi _{k}(s)\varphi _{k}(t),} where λ 1 ≥ λ 2 ≥ ⋯ ≥ 0 {\displaystyle \lambda _{1}\geq \lambda _{2}\geq \cdots \geq 0} are the eigenvalues and { φ 1 , φ 2 , ⋯ } {\displaystyle \{\varphi _{1},\varphi _{2},\cdots \}} are the orthonormal eigenfunctions of the linear Hilbert–Schmidt operator G : L 2 ( T ) → L 2 ( T ) , G ( f ) = ∫ T G ( s , t ) f ( s ) d s . {\displaystyle G:L^{2}({\mathcal {T}})\rightarrow L^{2}({\mathcal {T}}),\,G(f)=\int _{\mathcal {T}}G(s,t)f(s)ds.} By the Karhunen–Loève theorem, one can express the centered function in the eigenbasis, X ( t ) − μ ( t ) = ∑ k = 1 ∞ ξ k φ k ( t ) , {\displaystyle X(t)-\mu (t)=\sum _{k=1}^{\infty }\xi _{k}\varphi _{k}(t),} where ξ k = ∫ T ( X ( t ) − μ ( t ) ) φ k ( t ) d t {\displaystyle \xi _{k}=\int _{\mathcal {T}}(X(t)-\mu (t))\varphi _{k}(t)dt} is the k {\displaystyle k} -th principal component with the properties E ⁡ ( ξ k ) = 0 , Var ⁡ ( ξ k ) = λ k , {\displaystyle \operatorname {E} (\xi _{k})=0,\operatorname {Var} (\xi _{k})=\lambda _{k},} and E ⁡ ( ξ k ξ l ) = 0 for l ≠ k . {\displaystyle \operatorname {E} (\xi _{k}\xi _{l})=0{\text{ for }}l\neq k.} Then the k {\displaystyle k} -th mode of variation of X ( t ) {\displaystyle X(t)} is the set of functions, indexed by α {\displaystyle \alpha } , m k , α ( t ) = μ ( t ) ± α λ k φ k ( t ) , t ∈ T , α ∈ [ − A , A ] {\displaystyle m_{k,\alpha }(t)=\mu (t)\pm \alpha {\sqrt {\lambda _{k}}}\varphi _{k}(t),\ t\in {\mathcal {T}},\ \alpha \in [-A,A]} that are viewed simultaneously over the range of α {\displaystyle \alpha } , usually for A = 2 or 3 {\displaystyle A=2\ {\text{or}}\ 3} . == Estimation == The formulation above is derived from properties of the population. Estimation is needed in real-world applications. The key idea is to estimate mean and covariance. === Modes of variation in PCA === Suppose the data x 1 , x 2 , ⋯ , x n {\displaystyle \mathbf {x} _{1},\mathbf {x} _{2},\cdots ,\mathbf {x} _{n}} represent n {\displaystyle n} independent drawings from some p {\displaystyle p} -dimensional population X {\displaystyle \mathbf {X} } with mean vector μ {\displaystyle {\boldsymbol {\mu }}} and covariance matrix Σ {\displaystyle \mathbf {\Sigma } } . These data yield the sample mean vector x ¯ {\displaystyle {\overline {\mathbf {x} }}} , and the sample covariance matrix S {\displaystyle \mathbf {S} } with eigenvalue-eigenvector pairs ( λ ^ 1 , e ^ 1 ) , ( λ ^ 2 , e ^ 2 ) , ⋯ , ( λ ^ p , e ^ p ) {\displaystyle ({\hat {\lambda }}_{1},{\hat {\mathbf {e} }}_{1}),({\hat {\lambda }}_{2},{\hat {\mathbf {e} }}_{2}),\cdots ,({\hat {\lambda }}_{p},{\hat {\mathbf {e} }}_{p})} . Then the k {\displaystyle k} -th mode of variation of X {\displaystyle \mathbf {X} } can be estimated by m ^ k , α = x ¯ ± α λ ^ k e ^ k , α ∈ [ − A , A ] . {\displaystyle {\hat {\mathbf {m} }}_{k,\alpha }={\overline {\mathbf {x} }}\pm \alpha {\sqrt {{\hat {\lambda }}_{k}}}{\hat {\mathbf {e} }}_{k},\alpha \in [-A,A].} === Modes of variation in FPCA === Consider n {\displaystyle n} realizations X 1 ( t ) , X 2 ( t ) , ⋯ , X n ( t ) {\displaystyle X_{1}(t),X_{2}(t),\cdots ,X_{n}(t)} of a square-integrable random function X ( t ) , t ∈ T {\displaystyle X(t),t\in {\mathcal {T}}} with the mean function μ ( t ) = E ⁡ ( X ( t ) ) {\displaystyle \mu (t)=\operatorname {E} (X(t))} and the covariance function G ( s , t ) = Cov ⁡ ( X ( s ) , X ( t ) ) {\displaystyle G(s,t)=\operatorname {Cov} (X(s),X(t))} . Functional principal component analysis provides methods for the estimation of μ ( t ) {\displaystyle \mu (t)} and G ( s , t ) {\displaystyle G(s,t)} in detail, often involving point wise estimate and interpolation. Substituting estimates for the unknown quantities, the k {\displaystyle k} -th mode of variation of X ( t ) {\displaystyle X(t)} can be estimated by m ^ k , α ( t ) = μ ^ ( t ) ± α λ ^ k φ ^ k ( t ) , t ∈ T , α ∈ [ − A , A ] . {\displaystyle {\hat {m}}_{k,\alpha }(t)={\hat {\mu }}(t)\pm \alpha {\sqrt {{\hat {\lambda }}_{k}}}{\hat {\varphi }}_{k}(t),t\in {\mathcal {T}},\alpha \in [-A,A].} == Applications == Modes of variation are useful to visualize and describe the variation patterns in the data sorted by the eigenvalues. In real-world applications, modes of variation associated with eigencomponents allow to interpret complex data, such as the evolution of function traits and other infinite-dimensional data. To illustrate how modes of variation work in practice, two examples are shown in the graphs to the right, which display the first two modes of variation. The solid curve represents the sample mean function. The dashed, dot-dashed, and dotted curves correspond to modes of variation with α = ± 1 , ± 2 , {\displaystyle \alpha =\pm 1,\pm 2,} and ± 3 {\displaystyle \pm 3} , respectively. The first graph displays the first two modes of variation of female mortality data from 41 countries in 2003. The object of interest is log hazard function between ages 0 and 100 years. The first mode of variation suggests that the variation of female mortality is smaller for ages around 0 or 100, and larger for ages around 25. An appropriate and intuitive interpretation is that mortality around 25 is driven by accidental death, while around 0 or 100, mortality is related to congenital disease or natural death. Compared to female mortality

  Read more →
• 

  Genetic programming

  Genetic programming (GP) is an evolutionary algorithm, an artificial intelligence technique mimicking natural evolution, which operates on a population of programs. It applies the genetic operators selection according to a predefined fitness measure, mutation and crossover. The crossover operation involves swapping specified parts of selected pairs (parents) to produce new and different offspring that become part of the new generation of programs. Some programs not selected for reproduction are copied from the current generation to the new generation. Mutation involves substitution of some random part of a program with some other random part of a program. Then the selection and other operations are recursively applied to the new generation of programs. Typically, members of each new generation are on average more fit than the members of the previous generation, and the best-of-generation program is often better than the best-of-generation programs from previous generations. Termination of the evolution usually occurs when some individual program reaches a predefined proficiency or fitness level. It may and often does happen that a particular run of the algorithm results in premature convergence to some local maximum that is not a globally optimal or even good solution. Multiple runs (dozens to hundreds) are usually necessary to produce a very good result. It may also be necessary to have a large starting population size and variability of the individuals to avoid pathologies. == History == The first record of the proposal to evolve programs is probably that of Alan Turing in 1950 in "Computing Machinery and Intelligence". There was a gap of 25 years before the publication of John Holland's 'Adaptation in Natural and Artificial Systems' laid out the theoretical and empirical foundations of the science. In 1981, Richard Forsyth demonstrated the successful evolution of small programs, represented as trees, to perform classification of crime scene evidence for the UK Home Office. Although the idea of evolving programs, initially in the computer language Lisp, was current amongst John Holland's students, it was not until they organised the first Genetic Algorithms (GA) conference in Pittsburgh that Nichael Cramer published evolved programs in two specially designed languages, which included the first statement of modern "tree-based" genetic programming (that is, procedural languages organized in tree-based structures and operated on by suitably defined GA-operators). In 1988, John Koza (also a PhD student of John Holland) patented his invention of a GA for program evolution. This was followed by publication in the International Joint Conference on Artificial Intelligence IJCAI-89. Koza followed this with 205 publications on "genetic programming", a term coined by David Goldberg, also a PhD student of John Holland. However, it is the series of 4 books by Koza, starting in 1992 with accompanying videos, that really established GP. Subsequently, there was an enormous expansion of the number of publications with the Genetic Programming Bibliography, surpassing 10,000 entries. In 2010, Koza listed 77 results where genetic programming was human competitive. The departure of GP from the rigid, fixed-length representations typical of early GA models was not entirely without precedent. Early work on variable-length representations laid the groundwork. One notable example is messy genetic algorithms, which introduced irregular, variable-length chromosomes to address building block disruption and positional bias in standard GAs. Another precursor was robot trajectory programming, where genome representations encoded program instructions for robotic movements—structures inherently variable in length. Even earlier, unfixed-length representations were proposed in a doctoral dissertation by Cavicchio, who explored adaptive search using simulated evolution. His work provided foundational ideas for flexible program structures. In 1996, Koza started the annual Genetic Programming conference, which was followed in 1998 by the annual EuroGP conference, and the first book in a GP series edited by Koza. 1998 also saw the first GP textbook. GP continued to flourish, leading to the first specialist GP journal and three years later (2003) the annual Genetic Programming Theory and Practice (GPTP) workshop was established by Rick Riolo. Genetic programming papers continue to be published at a diversity of conferences and associated journals. Today there are nineteen GP books including several for students. === Foundational work in GP === Early work that set the stage for current genetic programming research topics and applications is diverse, and includes software synthesis and repair, predictive modeling, data mining, financial modeling, soft sensors, design, and image processing. Applications in some areas, such as design, often make use of intermediate representations, such as Fred Gruau's cellular encoding. Industrial uptake has been significant in several areas including finance, the chemical industry, bioinformatics and the steel industry. == Methods == === Program representation === GP evolves computer programs, traditionally represented in memory as tree structures. Trees can be easily evaluated in a recursive manner. Every internal node has an operator function and every terminal node has an operand, making mathematical expressions easy to evolve and evaluate. Thus traditionally GP favors the use of programming languages that naturally embody tree structures (for example, Lisp; other functional programming languages are also suitable). Non-tree representations have been suggested and successfully implemented, such as linear genetic programming, which perhaps suits the more traditional imperative languages. The commercial GP software Discipulus uses automatic induction of binary machine code ("AIM") to achieve better performance. μGP uses directed multigraphs to generate programs that fully exploit the syntax of a given assembly language. Multi expression programming uses three-address code for encoding solutions. Other program representations on which significant research and development have been conducted include programs for stack-based virtual machines, and sequences of integers that are mapped to arbitrary programming languages via grammars. Cartesian genetic programming is another form of GP, which uses a graph representation instead of the usual tree based representation to encode computer programs. Most representations have structurally noneffective code (introns). Such non-coding genes may seem to be useless because they have no effect on the performance of any one individual. However, they alter the probabilities of generating different offspring under the variation operators, and thus alter the individual's variational properties. Experiments seem to show faster convergence when using program representations that allow such non-coding genes, compared to program representations that do not have any non-coding genes. Instantiations may have both trees with introns and those without; the latter are called canonical trees. Special canonical crossover operators are introduced that maintain the canonical structure of parents in their children. === Initialisation === The methods for creation of the initial population include: Grow creates the individuals sequentially. Every GP tree is created starting from the root, creating functional nodes with children as well as terminal nodes up to a certain depth. Full is similar to the Grow. The difference is that all brunches in a tree are of same predetermined depth. Ramped half-and-half creates a population consisting of m d − 1 {\displaystyle md-1} parts and a maximum depth of m d {\displaystyle md} for its trees. The first part has a maximum depth of 2, second of 3 and so on up to the m d − 1 {\displaystyle md-1} -th part with maximum depth m d {\displaystyle md} . Half of every part is created by Grow, while the other part is created by Full. === Selection === Selection is a process whereby certain individuals are selected from the current generation that would serve as parents for the next generation. The individuals are selected probabilistically such that the better performing individuals have a higher chance of getting selected. The most commonly used selection method in GP is tournament selection, although other methods such as fitness proportionate selection, lexicase selection, and others have been demonstrated to perform better for many GP problems. Elitism, which involves seeding the next generation with the best individual (or best n individuals) from the current generation, is a technique sometimes employed to avoid regression. === Crossover === In genetic programming two fit individuals are chosen from the population to be parents for one or two children. In tree genetic programming, these parents are represented as inverted lisp like trees, with their root nodes at the top. In subtree cro

  Read more →
• 

  IDistance

  In pattern recognition, iDistance is an indexing and query processing technique for k-nearest neighbor queries on point data in multi-dimensional metric spaces. The kNN query is one of the hardest problems on multi-dimensional data, especially when the dimensionality of the data is high. iDistance is designed to process kNN queries in high-dimensional spaces efficiently and performs extremely well for skewed data distributions, which usually occur in real-life data sets. iDistance employs a two-phase search strategy involving an initial filtering of candidate regions and a subsequent refinement of results, an approach aligned with the Filter and Refine Principle (FRP). This means that the index first prunes the search space to eliminate unlikely candidates, then verifies the true nearest neighbors in a refinement step, following the general FRP paradigm used in database search algorithms. The iDistance index can also be augmented with machine learning models to learn data distributions for improved searching and storage of multi-dimensional data. == Indexing == Building the iDistance index has two steps: A number of reference points in the data space are chosen. There are various ways of choosing reference points. Using cluster centers as reference points is the most efficient way. The data points are partitioned into Voronoi cells based on well-chosen reference points. The distance between a data point and its closest reference point is calculated. This distance plus a scaling value is called the point's iDistance. By this means, points in a multi-dimensional space are mapped to one-dimensional values, and then a B+-tree can be adopted to index the points using the iDistance as the key. The figure on the right shows an example where three reference points (O1, O2, O3) are chosen. The data points are then mapped to a one-dimensional space and indexed in a B+-tree. Various extensions have been proposed to make the selection of reference points for effective query performance, including employing machine learning to learn the identification of reference points. == Query processing == To process a kNN query, the query is mapped to a number of one-dimensional range queries, which can be processed efficiently on a B+-tree. In the above figure, the query Q is mapped to a value in the B+-tree while the kNN search ``sphere" is mapped to a range in the B+-tree. The search sphere expands gradually until the k NNs are found. This corresponds to gradually expanding range searches in the B+-tree. The iDistance technique can be viewed as a way of accelerating the sequential scan. Instead of scanning records from the beginning to the end of the data file, the iDistance starts the scan from spots where the nearest neighbors can be obtained early with a very high probability. == Applications == The iDistance has been used in many applications including Image retrieval Video indexing Similarity search in P2P systems Mobile computing Recommender system == Historical background == The iDistance was first proposed by Cui Yu, Beng Chin Ooi, Kian-Lee Tan and H. V. Jagadish in 2001. Later, together with Rui Zhang, they improved the technique and performed a more comprehensive study on it in 2005.

  Read more →
• 

  Sorenson Squeeze

  Sorenson Squeeze was a software video encoding tool used to compress and convert video and audio files on Mac OS X or Windows operating systems. It was sold as a standalone tool and has also long been bundled with Avid Media Composer. == History == Sorenson Squeeze was first announced on July 17, 2001, as the first variable bit rate (VBR) compression application for Mac OS X, and was released on October 29 of that same year. By March 2002, Sorenson Squeeze became available for Windows OS. Sorenson Squeeze was originally released as a tool for encoding videos for the Web and QuickTime playback but began adding new codecs as more versions were released. The software was discontinued by Sorenson in January 2019, and correspondingly was no longer offered as part of Avid Media Composer. == Features == Squeeze included a number of features to improve video & audio quality. Features included: GPU accelerated H.264 encoding, adaptive bitrate encoding, HD encoding and Dolby certified AC3 Audio. Intelligent encoding presets available in Squeeze included: x265 (H.265) MainConcept H.264 and MainConcept H.264 CUDA. Adaptive bitrate encoding allows for optimal bitrate and error resilience based on network conditions, resulting in a dynamic adjustment of the video bitstream being delivered. It encoded to multiple formats including QuickTime, Windows Media, Flash Video, Silverlight, WebM & WMV. It uses multiple codecs, including the Sorenson codecs SV3 Pro and Spark, H.265, H.264, H.263, VP6, VC1, MPEG2, and many others. Squeeze operates on the Apple Macintosh and Microsoft Windows operating systems. Squeeze offers native plugins to Avid, Apple Final Cut Pro and Adobe Premiere (CS4, CS5) NLEs. Each copy of Squeeze included the Dolby Certified AC3 Consumer encoder. Squeeze also included a simplified review and approval process, which allows the user to automatically send secure, password protected videos for immediate review. Instant feedback is received via Web or mobile. == Versions == Sorenson Squeeze was released on October 29, 2001. Sorenson Squeeze for Macromedia Flash MX was released on March 14, 2002. Sorenson Squeeze 3 for MPEG-4 was released in January 2003. Sorenson Squeeze 3 Compression Suite was released in January 2003. Sorenson Squeeze 5 was released on March 31, 2008. Sorenson Squeeze was updated to version 5.1 on May 11, 2009. Sorenson Squeeze 6 was released on November 3, 2009. Sorenson Squeeze 7 was released January 25, 2011. Sorenson Squeeze 11 was released August 27, 2016. == Awards == Streaming Media magazine Readers’ Choice Award for Encoding Software for 2007, 2008, 2009 and 2010. 2008 Vanguard Award from Digital Content Producer magazine == Squeeze 7 system requirements == Windows Pentium IV-based computer or greater Windows XP, Vista or 7 32- and 64-bit compatible (including AVID 64-bit update); Faster performance on 64-bit systems 512 MB RAM 120 MB available hard drive space QuickTime 7.2 or later DirectX 9.0b or later Macintosh Intel-based processor Mac OS 10.4 or later 32- and 64-bit compatible; Faster performance on 64-bit systems 512 MB RAM 120 MB available hard drive space QuickTime 7.2 or later

  Read more →
• 

  Huber loss

  In statistics, the Huber loss is a loss function used in robust regression, that is less sensitive to outliers in data than the squared error loss. A variant for classification is also sometimes used. == Definition == The Huber loss function describes the penalty incurred by an estimation procedure f. Huber (1964) defines the loss function piecewise by L δ ( a ) = { 1 2 a 2 for | a | ≤ δ , δ ⋅ ( | a | − 1 2 δ ) , otherwise. {\displaystyle L_{\delta }(a)={\begin{cases}{\frac {1}{2}}{a^{2}}&{\text{for }}|a|\leq \delta ,\\[4pt]\delta \cdot \left(|a|-{\frac {1}{2}}\delta \right),&{\text{otherwise.}}\end{cases}}} This function is quadratic for small values of a, and linear for large values, with equal values and slopes of the different sections at the two points where | a | = δ {\displaystyle |a|=\delta } . The variable a often refers to the residuals, that is to the difference between the observed and predicted values a = y − f ( x ) {\displaystyle a=y-f(x)} , so the former can be expanded to L δ ( y , f ( x ) ) = { 1 2 ( y − f ( x ) ) 2 for | y − f ( x ) | ≤ δ , δ ⋅ ( | y − f ( x ) | − 1 2 δ ) , otherwise. {\displaystyle L_{\delta }(y,f(x))={\begin{cases}{\frac {1}{2}}{\left(y-f(x)\right)}^{2}&{\text{for }}\left|y-f(x)\right|\leq \delta ,\\[4pt]\delta \ \cdot \left(\left|y-f(x)\right|-{\frac {1}{2}}\delta \right),&{\text{otherwise.}}\end{cases}}} The Huber loss is the convolution of the absolute value function with the rectangular function, scaled and translated. Thus it "smoothens out" the former's corner at the origin. == Motivation == Two very commonly used loss functions are the squared loss, L ( a ) = a 2 {\displaystyle L(a)=a^{2}} , and the absolute loss, L ( a ) = | a | {\displaystyle L(a)=|a|} . The squared loss function results in an arithmetic mean-unbiased estimator, and the absolute-value loss function results in a median-unbiased estimator (in the one-dimensional case, and a geometric median-unbiased estimator for the multi-dimensional case). The squared loss has the disadvantage that it has the tendency to be dominated by outliers—when summing over a set of a {\displaystyle a} 's (as in ∑ i = 1 n L ( a i ) {\textstyle \sum _{i=1}^{n}L(a_{i})} ), the sample mean is influenced too much by a few particularly large a {\displaystyle a} -values when the distribution is heavy tailed: in terms of estimation theory, the asymptotic relative efficiency of the mean is poor for heavy-tailed distributions. As defined above, the Huber loss function is strongly convex in a uniform neighborhood of its minimum a = 0 {\displaystyle a=0} ; at the boundary of this uniform neighborhood, the Huber loss function has a differentiable extension to an affine function at points a = − δ {\displaystyle a=-\delta } and a = δ {\displaystyle a=\delta } . These properties allow it to combine much of the sensitivity of the mean-unbiased, minimum-variance estimator of the mean (using the quadratic loss function) and the robustness of the median-unbiased estimator (using the absolute value function). == Pseudo-Huber loss function == The Pseudo-Huber loss function can be used as a smooth approximation of the Huber loss function. It combines the best properties of L2 squared loss and L1 absolute loss by being strongly convex when close to the target/minimum and less steep for extreme values. The scale at which the Pseudo-Huber loss function transitions from L2 loss for values close to the minimum to L1 loss for extreme values and the steepness at extreme values can be controlled by the δ {\displaystyle \delta } value. The Pseudo-Huber loss function ensures that derivatives are continuous for all degrees. It is defined as L δ ( a ) = δ 2 ( 1 + ( a / δ ) 2 − 1 ) . {\displaystyle L_{\delta }(a)=\delta ^{2}\left({\sqrt {1+(a/\delta )^{2}}}-1\right).} As such, this function approximates a 2 / 2 {\displaystyle a^{2}/2} for small values of a {\displaystyle a} , and approximates a straight line with slope δ {\displaystyle \delta } for large values of a {\displaystyle a} . While the above is the most common form, other smooth approximations of the Huber loss function also exist. == Variant for classification == For classification purposes, a variant of the Huber loss called modified Huber is sometimes used. Given a prediction f ( x ) {\displaystyle f(x)} (a real-valued classifier score) and a true binary class label y ∈ { + 1 , − 1 } {\displaystyle y\in \{+1,-1\}} , the modified Huber loss is defined as L ( y , f ( x ) ) = { max ( 0 , 1 − y f ( x ) ) 2 for y f ( x ) > − 1 , − 4 y f ( x ) otherwise. {\displaystyle L(y,f(x))={\begin{cases}\max(0,1-y\,f(x))^{2}&{\text{for }}\,\,y\,f(x)>-1,\\[4pt]-4y\,f(x)&{\text{otherwise.}}\end{cases}}} The term max ( 0 , 1 − y f ( x ) ) {\displaystyle \max(0,1-y\,f(x))} is the hinge loss used by support vector machines; the quadratically smoothed hinge loss is a generalization of L {\displaystyle L} . == Applications == The Huber loss function is used in robust statistics, M-estimation and additive modelling.

  Read more →
• 

  Junction tree algorithm

  The junction tree algorithm (also known as 'Clique Tree') is a method used in machine learning to extract marginalization in general graphs. In essence, it entails performing belief propagation on a modified graph called a junction tree. The graph is called a tree because it branches into different sections of data; nodes of variables are the branches. The basic premise is to eliminate cycles by clustering them into single nodes. Multiple extensive classes of queries can be compiled at the same time into larger structures of data. There are different algorithms to meet specific needs and for what needs to be calculated. Inference algorithms gather new developments in the data and calculate it based on the new information provided. == Junction tree algorithm == === Hugin algorithm === If the graph is directed then moralize it to make it un-directed. Introduce the evidence. Triangulate the graph to make it chordal. Construct a junction tree from the triangulated graph (we will call the vertices of the junction tree "supernodes"). Propagate the probabilities along the junction tree (via belief propagation) Note that this last step is inefficient for graphs of large treewidth. Computing the messages to pass between supernodes involves doing exact marginalization over the variables in both supernodes. Performing this algorithm for a graph with treewidth k will thus have at least one computation which takes time exponential in k. It is a message passing algorithm. The Hugin algorithm takes fewer computations to find a solution compared to Shafer-Shenoy. === Shafer-Shenoy algorithm === Computed recursively Multiple recursions of the Shafer-Shenoy algorithm results in Hugin algorithm Found by the message passing equation Separator potentials are not stored The Shafer-Shenoy algorithm is the sum product of a junction tree. It is used because it runs programs and queries more efficiently than the Hugin algorithm. The algorithm makes calculations for conditionals for belief functions possible. Joint distributions are needed to make local computations happen. === Underlying theory === The first step concerns only Bayesian networks, and is a procedure to turn a directed graph into an undirected one. We do this because it allows for the universal applicability of the algorithm, regardless of direction. The second step is setting variables to their observed value. This is usually needed when we want to calculate conditional probabilities, so we fix the value of the random variables we condition on. Those variables are also said to be clamped to their particular value. The third step is to ensure that graphs are made chordal if they aren't already chordal. This is the first essential step of the algorithm. It makes use of the following theorem: Theorem: For an undirected graph, G, the following properties are equivalent: Graph G is triangulated. The clique graph of G has a junction tree. There is an elimination ordering for G that does not lead to any added edges. Thus, by triangulating a graph, we make sure that the corresponding junction tree exists. A usual way to do this, is to decide an elimination order for its nodes, and then run the Variable elimination algorithm. The variable elimination algorithm states that the algorithm must be run each time there is a different query. This will result to adding more edges to the initial graph, in such a way that the output will be a chordal graph. All chordal graphs have a junction tree. The next step is to construct the junction tree. To do so, we use the graph from the previous step, and form its corresponding clique graph. Now the next theorem gives us a way to find a junction tree: Theorem: Given a triangulated graph, weight the edges of the clique graph by their cardinality, |A∩B|, of the intersection of the adjacent cliques A and B. Then any maximum-weight spanning tree of the clique graph is a junction tree. So, to construct a junction tree we just have to extract a maximum weight spanning tree out of the clique graph. This can be efficiently done by, for example, modifying Kruskal's algorithm. The last step is to apply belief propagation to the obtained junction tree. Usage: A junction tree graph is used to visualize the probabilities of the problem. The tree can become a binary tree to form the actual building of the tree. A specific use could be found in auto encoders, which combine the graph and a passing network on a large scale automatically. === Inference Algorithms === Loopy belief propagation: A different method of interpreting complex graphs. The loopy belief propagation is used when an approximate solution is needed instead of the exact solution. It is an approximate inference. Cutset conditioning: Used with smaller sets of variables. Cutset conditioning allows for simpler graphs that are easier to read but are not exact.

  Read more →