AI Face Time

AI Face Time — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Period-tracking app

  Period-tracking apps are mobile applications used to track the menstrual cycle. They may be used to predict menstruation, to plan fertility, and to track health. Examples include Clue, Glow, and Flo. == Function == Users enter their dates of menstruation, and frequently other experiences such as vaginal discharge and spotting; premenstrual syndrome; changes in mood; menstrual cramps and other pain; and other symptoms such as appetite changes, bloating, and acne. The apps predict the date of users' next period, and often also their ovulation and fertile window. Some apps have additional features such as contraceptive reminders, educational content, tracking modes for use during pregnancy, or the ability to share one's menstrual cycle data with a partner. == Privacy == Period-tracking apps collect personal health data, potentially raising concerns about privacy. Researchers have warned that data may be transferred to third parties and used for consumer profiling and targeted advertising, used for employment and health insurance discrimination, or used to prosecute users for seeking abortions. After the 2022 decision by the United States Supreme Court to overturn Roe v. Wade, and the bans and restrictions on abortion in many US states that followed, many American women uninstalled the apps amidst fear that the data could be accessed by law enforcement and used to prosecute users. WIRED published a ranking of several period-tracking apps by data privacy.

  Read more →
• 

  Unrestricted algorithm

  An unrestricted algorithm is an algorithm for the computation of a mathematical function that puts no restrictions on the range of the argument or on the precision that may be demanded in the result. The idea of such an algorithm was put forward by C. W. Clenshaw and F. W. J. Olver in a paper published in 1980. In the problem of developing algorithms for computing, as regards the values of a real-valued function of a real variable (e.g., g[x] in "restricted" algorithms), the error that can be tolerated in the result is specified in advance. An interval on the real line would also be specified for values when the values of a function are to be evaluated. Different algorithms may have to be applied for evaluating functions outside the interval. An unrestricted algorithm envisages a situation in which a user may stipulate the value of x and also the precision required in g(x) quite arbitrarily. The algorithm should then produce an acceptable result without failure.

  Read more →
• 

  Browsing

  Browsing is a kind of orienting strategy. It is supposed to identify something of relevance for the browsing organism. In context of humans, it is a metaphor taken from the animal kingdom. It is used, for example, about people browsing open shelves in libraries, window shopping, or browsing databases or the Internet. In library and information science, it is an important subject, both purely theoretically and as applied science aiming at designing interfaces which support browsing activities for the user. == Definition == In 2011, Birger Hjørland provided the following definition: "Browsing is a quick examination of the relevance of a number of objects which may or may not lead to a closer examination or acquisition/selection of (some of) these objects. It is a kind of orienting strategy that is formed by our "theories", "expectations" and "subjectivity". == Controversies == As with any kind of human psychology, browsing can be understood in biological, behavioral, or cognitive terms on the one hand or in social, historical, and cultural terms on the other hand. In 2007, Marcia Bates researched browsing from "behavioural" approaches, while Hjørland (2011a+b) defended a social view. Bates found that browsing is rooted in our history as exploratory, motile animals hunting for food and nesting opportunities. According to Hjørland (2011a), on the other hand, Marcia Bates' browsing for information about browsing is governed by her behavioral assumptions, while Hjørland's browsing for information about browsing is governed by his socio-cultural understanding of human psychology. In short: Human browsing is based on our conceptions and interests. === Is browsing a random activity? === Browsing is often understood as a random activity. Dictionary.com, for example, has this definition: "to glance at random through a book, magazine, etc.". Hjørland suggests, however, that browsing is an activity that is governed by our metatheories. We may dynamically change our theories and conceptions but when we browse, the activity is governed by the interests, conceptions, priorities and metatheories that we have at that time. Therefore, browsing is not totally random. == Browsing versus analytical search strategies == In 1997, Gary Marchionini wrote: "A fundamental distinction is made between analytical and browsing strategies [...]. Analytical strategies depend on careful planning, the recall of query terms, and iterative query reformulations and examinations of results. Browsing strategies are heuristic and opportunistic and depend on recognizing relevant information. Analytic strategies are batch oriented and half duplex (turn talking) like human conversation, whereas browsing strategies are more interactive, real-time exchanges and collaborations between the information seeker and the information system. Browsing strategies demand a lower cognitive load in advance and a steadier attentional load throughout the information-seeking process. When it comes to Browsing, giblets are amazing." == Orienting strategies == Some sociologists, such as Berger and Zelditch in 1993, Wagner in 1984, and Wagner & Berger in 1985, have used the term "orienting strategies". They find that orienting strategies should be understood as metatheories: "Consider the very large proportion of sociological theory that is in the form of metatheory. It is discussion about theory: about what concepts it should include, about how those concepts should be linked, and about how theory should be studied. Similar to Kuhn’s paradigms, theories of this sort provide guidelines or strategies for understanding social phenomena and suggest the proper orientation of the theorist to these phenomena; they are orienting strategies. Textbooks in theory frequently focus on orienting strategies such as functionalism, exchange, or ethnomethodology." Sociologists thus use metatheories as orienting strategies. We may generalize and say that all people use metatheories as orienting strategies and that this is what direct our attention and also our browsing – also when we are not conscious about it.

  Read more →
• 

  DONE

  The Data-based Online Nonlinear Extremumseeker (DONE) algorithm is a black-box optimization algorithm. DONE models the unknown cost function and attempts to find an optimum of the underlying function. The DONE algorithm is suitable for optimizing costly and noisy functions and does not require derivatives. An advantage of DONE over similar algorithms, such as Bayesian optimization, is that the computational cost per iteration is independent of the number of function evaluations. == Methods == The DONE algorithm was first proposed by Hans Verstraete and Sander Wahls in 2015. The algorithm fits a surrogate model based on random Fourier features and then uses a well-known L-BFGS algorithm to find an optimum of the surrogate model. == Applications == DONE was first demonstrated for maximizing the signal in optical coherence tomography measurements, but has since then been applied to various other applications. For example, it was used to help extending the field of view in light sheet fluorescence microscopy.

  Read more →
• 

  Proximal gradient methods for learning

  Proximal gradient (forward backward splitting) methods for learning is an area of research in optimization and statistical learning theory which studies algorithms for a general class of convex regularization problems where the regularization penalty may not be differentiable. One such example is ℓ 1 {\displaystyle \ell _{1}} regularization (also known as Lasso) of the form min w ∈ R d 1 n ∑ i = 1 n ( y i − ⟨ w , x i ⟩ ) 2 + λ ‖ w ‖ 1 , where x i ∈ R d and y i ∈ R . {\displaystyle \min _{w\in \mathbb {R} ^{d}}{\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-\langle w,x_{i}\rangle )^{2}+\lambda \|w\|_{1},\quad {\text{ where }}x_{i}\in \mathbb {R} ^{d}{\text{ and }}y_{i}\in \mathbb {R} .} Proximal gradient methods offer a general framework for solving regularization problems from statistical learning theory with penalties that are tailored to a specific problem application. Such customized penalties can help to induce certain structure in problem solutions, such as sparsity (in the case of lasso) or group structure (in the case of group lasso). == Relevant background == Proximal gradient methods are applicable in a wide variety of scenarios for solving convex optimization problems of the form min x ∈ H F ( x ) + R ( x ) , {\displaystyle \min _{x\in {\mathcal {H}}}F(x)+R(x),} where F {\displaystyle F} is convex and differentiable with Lipschitz continuous gradient, R {\displaystyle R} is a convex, lower semicontinuous function which is possibly nondifferentiable, and H {\displaystyle {\mathcal {H}}} is some set, typically a Hilbert space. The usual criterion of x {\displaystyle x} minimizes F ( x ) + R ( x ) {\displaystyle F(x)+R(x)} if and only if ∇ ( F + R ) ( x ) = 0 {\displaystyle \nabla (F+R)(x)=0} in the convex, differentiable setting is now replaced by 0 ∈ ∂ ( F + R ) ( x ) , {\displaystyle 0\in \partial (F+R)(x),} where ∂ φ {\displaystyle \partial \varphi } denotes the subdifferential of a real-valued, convex function φ {\displaystyle \varphi } . Given a convex function φ : H → R {\displaystyle \varphi :{\mathcal {H}}\to \mathbb {R} } an important operator to consider is its proximal operator prox φ : H → H {\displaystyle \operatorname {prox} _{\varphi }:{\mathcal {H}}\to {\mathcal {H}}} defined by prox φ ⁡ ( u ) = arg ⁡ min x ∈ H φ ( x ) + 1 2 ‖ u − x ‖ 2 2 , {\displaystyle \operatorname {prox} _{\varphi }(u)=\operatorname {arg} \min _{x\in {\mathcal {H}}}\varphi (x)+{\frac {1}{2}}\|u-x\|_{2}^{2},} which is well-defined because of the strict convexity of the ℓ 2 {\displaystyle \ell _{2}} norm. The proximal operator can be seen as a generalization of a projection. We see that the proximity operator is important because x ∗ {\displaystyle x^{}} is a minimizer to the problem min x ∈ H F ( x ) + R ( x ) {\displaystyle \min _{x\in {\mathcal {H}}}F(x)+R(x)} if and only if x ∗ = prox γ R ⁡ ( x ∗ − γ ∇ F ( x ∗ ) ) , {\displaystyle x^{}=\operatorname {prox} _{\gamma R}\left(x^{}-\gamma \nabla F(x^{})\right),} where γ > 0 {\displaystyle \gamma >0} is any positive real number. === Moreau decomposition === One important technique related to proximal gradient methods is the Moreau decomposition, which decomposes the identity operator as the sum of two proximity operators. Namely, let φ : X → R {\displaystyle \varphi :{\mathcal {X}}\to \mathbb {R} } be a lower semicontinuous, convex function on a vector space X {\displaystyle {\mathcal {X}}} . We define its Fenchel conjugate φ ∗ : X → R {\displaystyle \varphi ^{}:{\mathcal {X}}\to \mathbb {R} } to be the function φ ∗ ( u ) := sup x ∈ X ⟨ x , u ⟩ − φ ( x ) . {\displaystyle \varphi ^{}(u):=\sup _{x\in {\mathcal {X}}}\langle x,u\rangle -\varphi (x).} The general form of Moreau's decomposition states that for any x ∈ X {\displaystyle x\in {\mathcal {X}}} and any γ > 0 {\displaystyle \gamma >0} that x = prox γ φ ⁡ ( x ) + γ prox φ ∗ / γ ⁡ ( x / γ ) , {\displaystyle x=\operatorname {prox} _{\gamma \varphi }(x)+\gamma \operatorname {prox} _{\varphi ^{}/\gamma }(x/\gamma ),} which for γ = 1 {\displaystyle \gamma =1} implies that x = prox φ ⁡ ( x ) + prox φ ∗ ⁡ ( x ) {\displaystyle x=\operatorname {prox} _{\varphi }(x)+\operatorname {prox} _{\varphi ^{}}(x)} . The Moreau decomposition can be seen to be a generalization of the usual orthogonal decomposition of a vector space, analogous with the fact that proximity operators are generalizations of projections. In certain situations it may be easier to compute the proximity operator for the conjugate φ ∗ {\displaystyle \varphi ^{}} instead of the function φ {\displaystyle \varphi } , and therefore the Moreau decomposition can be applied. This is the case for group lasso. == Lasso regularization == Consider the regularized empirical risk minimization problem with square loss and with the ℓ 1 {\displaystyle \ell _{1}} norm as the regularization penalty: min w ∈ R d 1 n ∑ i = 1 n ( y i − ⟨ w , x i ⟩ ) 2 + λ ‖ w ‖ 1 , {\displaystyle \min _{w\in \mathbb {R} ^{d}}{\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-\langle w,x_{i}\rangle )^{2}+\lambda \|w\|_{1},} where x i ∈ R d and y i ∈ R . {\displaystyle x_{i}\in \mathbb {R} ^{d}{\text{ and }}y_{i}\in \mathbb {R} .} The ℓ 1 {\displaystyle \ell _{1}} regularization problem is sometimes referred to as lasso (least absolute shrinkage and selection operator). Such ℓ 1 {\displaystyle \ell _{1}} regularization problems are interesting because they induce sparse solutions, that is, solutions w {\displaystyle w} to the minimization problem have relatively few nonzero components. Lasso can be seen to be a convex relaxation of the non-convex problem min w ∈ R d 1 n ∑ i = 1 n ( y i − ⟨ w , x i ⟩ ) 2 + λ ‖ w ‖ 0 , {\displaystyle \min _{w\in \mathbb {R} ^{d}}{\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-\langle w,x_{i}\rangle )^{2}+\lambda \|w\|_{0},} where ‖ w ‖ 0 {\displaystyle \|w\|_{0}} denotes the ℓ 0 {\displaystyle \ell _{0}} "norm", which is the number of nonzero entries of the vector w {\displaystyle w} . Sparse solutions are of particular interest in learning theory for interpretability of results: a sparse solution can identify a small number of important factors. === Solving for L1 proximity operator === For simplicity we restrict our attention to the problem where λ = 1 {\displaystyle \lambda =1} . To solve the problem min w ∈ R d 1 n ∑ i = 1 n ( y i − ⟨ w , x i ⟩ ) 2 + ‖ w ‖ 1 , {\displaystyle \min _{w\in \mathbb {R} ^{d}}{\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-\langle w,x_{i}\rangle )^{2}+\|w\|_{1},} we consider our objective function in two parts: a convex, differentiable term F ( w ) = 1 n ∑ i = 1 n ( y i − ⟨ w , x i ⟩ ) 2 {\displaystyle F(w)={\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-\langle w,x_{i}\rangle )^{2}} and a convex function R ( w ) = ‖ w ‖ 1 {\displaystyle R(w)=\|w\|_{1}} . Note that R {\displaystyle R} is not strictly convex. Let us compute the proximity operator for R ( w ) {\displaystyle R(w)} . First we find an alternative characterization of the proximity operator prox R ⁡ ( x ) {\displaystyle \operatorname {prox} _{R}(x)} as follows: u = prox R ⁡ ( x ) ⟺ 0 ∈ ∂ ( R ( u ) + 1 2 ‖ u − x ‖ 2 2 ) ⟺ 0 ∈ ∂ R ( u ) + u − x ⟺ x − u ∈ ∂ R ( u ) . {\displaystyle {\begin{aligned}u=\operatorname {prox} _{R}(x)\iff &0\in \partial \left(R(u)+{\frac {1}{2}}\|u-x\|_{2}^{2}\right)\\\iff &0\in \partial R(u)+u-x\\\iff &x-u\in \partial R(u).\end{aligned}}} For R ( w ) = ‖ w ‖ 1 {\displaystyle R(w)=\|w\|_{1}} it is easy to compute ∂ R ( w ) {\displaystyle \partial R(w)} : the i {\displaystyle i} th entry of ∂ R ( w ) {\displaystyle \partial R(w)} is precisely ∂ | w i | = { 1 , w i > 0 − 1 , w i < 0 [ − 1 , 1 ] , w i = 0. {\displaystyle \partial |w_{i}|={\begin{cases}1,&w_{i}>0\\-1,&w_{i}<0\\\left[-1,1\right],&w_{i}=0.\end{cases}}} Using the recharacterization of the proximity operator given above, for the choice of R ( w ) = ‖ w ‖ 1 {\displaystyle R(w)=\|w\|_{1}} and γ > 0 {\displaystyle \gamma >0} we have that prox γ R ⁡ ( x ) {\displaystyle \operatorname {prox} _{\gamma R}(x)} is defined entrywise by ( prox γ R ⁡ ( x ) ) i = { x i − γ , x i > γ 0 , | x i | ≤ γ x i + γ , x i < − γ , {\displaystyle \left(\operatorname {prox} _{\gamma R}(x)\right)_{i}={\begin{cases}x_{i}-\gamma ,&x_{i}>\gamma \\0,&|x_{i}|\leq \gamma \\x_{i}+\gamma ,&x_{i}<-\gamma ,\end{cases}}} which is known as the soft thresholding operator S γ ( x ) = prox γ ‖ ⋅ ‖ 1 ⁡ ( x ) {\displaystyle S_{\gamma }(x)=\operatorname {prox} _{\gamma \|\cdot \|_{1}}(x)} . === Fixed point iterative schemes === To finally solve the lasso problem we consider the fixed point equation shown earlier: x ∗ = prox γ R ⁡ ( x ∗ − γ ∇ F ( x ∗ ) ) . {\displaystyle x^{}=\operatorname {prox} _{\gamma R}\left(x^{}-\gamma \nabla F(x^{})\right).} Given that we have computed the form of the proximity operator explicitly, then we can define a standard fixed point iteration procedure. Namely, fix some initial w 0 ∈ R d {\displaystyle w^{0}\in \mathbb {R} ^{d}} , and for k = 1 , 2 , … {\displaystyle k=1,2,\ldots } define w k + 1 = S γ ( w k − γ ∇ F ( w k ) ) . {\displaystyle w^{k+1}=S_{\gamma }\left(w^{k}-\gamma \nabla F\l

  Read more →
• 

  Chinese speech synthesis

  Chinese speech synthesis is the application of speech synthesis to the Chinese language (usually Standard Chinese). It poses additional difficulties due to Chinese characters frequently having different pronunciations in different contexts and the complex prosody, which is essential to convey the meaning of words, and sometimes the difficulty in obtaining agreement among native speakers concerning what the correct pronunciation is of certain phonemes. == Concatenation (Ekho and KeyTip) == Recordings can be concatenated in any desired combination, but the joins sound forced (as is usual for simple concatenation-based speech synthesis) and this can severely affect prosody; these synthesizers are also inflexible in terms of speed and expression. However, because these synthesizers do not rely on a corpus, there is no noticeable degradation in performance when they are given more unusual or awkward phrases. Ekho is an open source TTS which simply concatenates sampled syllables. It currently supports Cantonese, Mandarin, and experimentally Korean. Some of the Mandarin syllables have been pitched-normalised in Praat. A modified version of these is used in Gradint's "synthesis from partials". cjkware.com used to ship a product called KeyTip Putonghua Reader which worked similarly; it contained 120 Megabytes of sound recordings (GSM-compressed to 40 Megabytes in the evaluation version), comprising 10,000 multi-syllable dictionary words plus single-syllable recordings in 6 different prosodies (4 tones, neutral tone, and an extra third-tone recording for use at the end of a phrase). == Lightweight synthesizers (eSpeak and Yuet) == The lightweight open-source speech project eSpeak, which has its own approach to synthesis, has experimented with Mandarin and Cantonese. eSpeak was used by Google Translate from May 2010 until December 2010. The commercial product "Yuet" is also lightweight (it is intended to be suitable for resource-constrained environments like embedded systems); it was written from scratch in ANSI C starting from 2013. Yuet claims a built-in NLP model that does not require a separate dictionary; the speech synthesised by the engine claims clear word boundaries and emphasis on appropriate words. Communication with its author is required to obtain a copy. Both eSpeak and Yuet can synthesis speech for Cantonese and Mandarin from the same input text, and can output the corresponding romanisation (for Cantonese, Yuet uses Yale and eSpeak uses Jyutping; both use Pinyin for Mandarin). eSpeak does not concern itself with word boundaries when these don't change the question of which syllable should be spoken. == Corpus-based == A "corpus-based" approach can sound very natural in most cases but can err in dealing with unusual phrases if they can't be matched with the corpus. The synthesiser engine is typically very large (hundreds or even thousands of megabytes) due to the size of the corpus. === iFlyTek === Anhui USTC iFlyTek Co., Ltd (iFlyTek) published a W3C paper in which they adapted Speech Synthesis Markup Language to produce a mark-up language called Chinese Speech Synthesis Markup Language (CSSML) which can include additional markup to clarify the pronunciation of characters and to add some prosody information. The amount of data involved is not disclosed by iFlyTek but can be seen from the commercial products that iFlyTek have licensed their technology to; for example, Bider's SpeechPlus is a 1.3 Gigabyte download, 1.2 Gigabytes of which is used for the highly compressed data for a single Chinese voice. iFlyTek's synthesiser can also synthesise mixed Chinese and English text with the same voice (e.g. Chinese sentences containing some English words); they claim their English synthesis to be "average". The iFlyTek corpus appears to be heavily dependent on Chinese characters, and it is not possible to synthesize from pinyin alone. It is sometimes possible by means of CSSML to add pinyin to the characters to disambiguate between multiple possible pronunciations, but this does not always work. === NeoSpeech === There is an online interactive demonstration for NeoSpeech speech synthesis, which accepts Chinese characters and also pinyin if it's enclosed in their proprietary "VTML" markup. === Mac OS === Mac OS had Chinese speech synthesizers available up to version 9. This was removed in 10.0 and reinstated in 10.7 (Lion). === Historical corpus-based synthesizers (no longer available) === A corpus-based approach was taken by Tsinghua University in SinoSonic, with the Harbin dialect voice data taking 800 Megabytes. This was planned to be offered as a download but the link was never activated. Nowadays, only references to it can be found on Internet Archive. Bell Labs' approach, which was demonstrated online in 1997 but subsequently removed, was described in a monograph "Multilingual Text-to-Speech Synthesis: The Bell Labs Approach" (Springer, October 31, 1997, ISBN 978-0-7923-8027-6), and the former employee who was responsible for the project, Chilin Shih (who subsequently worked at the University of Illinois) put some notes about her methods on her website.

  Read more →
• 

  TurboQuant

  TurboQuant is an online vector quantization algorithm for compressing high-dimensional Euclidean vectors while preserving their geometric structure. It was proposed in 2025 by Amir Zandieh, Majid Daliri, Majid Hadian, and Vahab Mirrokni in the paper TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate. The paper lists Zandieh and Mirrokni as affiliated with Google Research, Daliri with New York University, and Hadian with Google DeepMind. The method was developed for applications including large language model (LLM) inference, key–value (KV) cache compression, vector databases, and nearest neighbor search. TurboQuant consists of two related algorithms: TurboQuantmse, which is optimized for mean squared error (MSE), and TurboQuantprod, which is optimized for unbiased inner product estimation. The algorithm uses a random rotation of input vectors, applies scalar quantizers to the rotated coordinates, and, for inner-product estimation, applies a one-bit Quantized Johnson–Lindenstrauss (QJL) transform to the residual error. == Background == Vector quantization is a compression method that maps high-dimensional vectors to a finite set of codewords. The problem has roots in Shannon's source coding theory and rate–distortion theory. In machine learning and information retrieval, vector quantization is used to reduce the memory required to store embeddings, activation vectors, and other numerical representations. In Transformer-based large language models, the KV cache stores key and value vectors from previous tokens during autoregressive decoding. The size of this cache grows with context length, the number of attention heads, and the number of concurrent requests, making it a major memory bottleneck in LLM serving. Similar compression problems appear in vector search, where large collections of embedding vectors must be stored and searched efficiently. Earlier approaches to vector quantization include product quantization, scalar quantization, and data-dependent k-means codebook construction. The TurboQuant paper argues that many existing methods either require offline preprocessing and calibration or suffer from suboptimal distortion guarantees in online settings. == Algorithm == === TurboQuantmse === TurboQuantmse is the version of the algorithm optimized for mean-squared error. For a unit vector x ∈ S d − 1 {\displaystyle x\in S^{d-1}} , the algorithm first applies a random rotation matrix Π ∈ R d × d {\displaystyle \Pi \in \mathbb {R} ^{d\times d}} and sets z = Π x {\displaystyle z=\Pi x} . Each coordinate of the rotated vector follows a shifted and scaled beta distribution, which converges to a normal distribution in high dimensions. In high dimensions, distinct coordinates also become nearly independent, allowing the algorithm to apply scalar quantizers independently to each coordinate. The scalar quantizer is constructed by solving a one-dimensional continuous k-means or Lloyd–Max quantization problem. If the centroids are c 1 , c 2 , … , c 2 b {\displaystyle c_{1},c_{2},\ldots ,c_{2^{b}}} , the quantization step stores, for each coordinate, i d x j = ⁡ a r g m i n k ∈ [ 2 b ] | z j − c k | . {\displaystyle \mathrm {idx} _{j}=\operatorname {} {arg\,min}_{k\in [2^{b}]}|z_{j}-c_{k}|.} During dequantization, the stored index for each coordinate is replaced by the corresponding centroid, giving a reconstructed rotated vector z ~ {\displaystyle {\tilde {z}}} . The algorithm then rotates back: x ~ = Π ⊤ z ~ . {\displaystyle {\tilde {x}}=\Pi ^{\top }{\tilde {z}}.} The paper gives the following bound for TurboQuantmse: D m s e ≤ 3 π 2 ⋅ 1 4 b . {\displaystyle D_{\mathrm {mse} }\leq {\frac {\sqrt {3\pi }}{2}}\cdot {\frac {1}{4^{b}}}.} It also reports finer-grained MSE values of approximately 0.36, 0.117, 0.03, and 0.009 for bit-widths b = 1 , 2 , 3 , 4 {\displaystyle b=1,2,3,4} , respectively. === TurboQuantprod === TurboQuantprod is optimized for unbiased inner-product estimation. The authors note that an MSE-optimized quantizer may introduce bias when used to estimate inner products. To address this, TurboQuantprod first applies TurboQuantmse with bit-width b − 1 {\displaystyle b-1} , then applies a one-bit Quantized Johnson–Lindenstrauss transform to the remaining residual vector. Let r = x − Q m s e − 1 ( Q m s e ( x ) ) {\displaystyle r=x-Q_{\mathrm {mse} }^{-1}(Q_{\mathrm {mse} }(x))} be the residual after MSE quantization, and let γ = ‖ r ‖ 2 {\displaystyle \gamma =\|r\|_{2}} . The QJL step stores a sign vector for the residual. For γ ≠ 0 {\displaystyle \gamma \neq 0} , this can be written using the normalized residual u = r / γ {\displaystyle u=r/\gamma } : q j l = sign ⁡ ( S u ) , {\displaystyle qjl=\operatorname {sign} (Su),} where S ∈ R d × d {\displaystyle S\in \mathbb {R} ^{d\times d}} is a random projection matrix. Since the sign function is invariant under positive rescaling, this is equivalent to sign ⁡ ( S r ) {\displaystyle \operatorname {sign} (Sr)} when r ≠ 0 {\displaystyle r\neq 0} . If γ = 0 {\displaystyle \gamma =0} , the residual correction is zero. TurboQuantprod stores the MSE quantization, the QJL sign vector, and the residual norm: Q p r o d ( x ) = [ Q m s e ( x ) , q j l , γ ] . {\displaystyle Q_{\mathrm {prod} }(x)=\left[Q_{\mathrm {mse} }(x),qjl,\gamma \right].} The dequantized vector is reconstructed as x ~ = x ~ m s e + π / 2 d γ S ⊤ q j l . {\displaystyle {\tilde {x}}={\tilde {x}}_{\mathrm {mse} }+{\frac {\sqrt {\pi /2}}{d}}\,\gamma S^{\top }qjl.} The paper proves that TurboQuantprod is unbiased for inner-product estimation: E x ~ [ ⟨ y , x ~ ⟩ ] = ⟨ y , x ⟩ . {\displaystyle \mathbb {E} _{\tilde {x}}\left[\langle y,{\tilde {x}}\rangle \right]=\langle y,x\rangle .} It also gives the distortion bound D p r o d ≤ 3 π 2 ⋅ ‖ y ‖ 2 2 d ⋅ 1 4 b . {\displaystyle D_{\mathrm {prod} }\leq {\frac {\sqrt {3\pi }}{2}}\cdot {\frac {\|y\|_{2}^{2}}{d}}\cdot {\frac {1}{4^{b}}}.} == Performance and applications == The TurboQuant paper reports that the algorithm achieves near-optimal distortion rates within a small constant factor of information-theoretic lower bounds. The authors report that, for KV cache quantization, TurboQuant achieved quality neutrality at 3.5 bits per channel and marginal degradation at 2.5 bits per channel. In long-context LLM experiments using Llama 3.1 8B Instruct, the paper evaluated the method on a "needle-in-a-haystack" retrieval task with document lengths from 4,000 to 104,000 tokens. It reported that TurboQuant matched the uncompressed full-precision baseline while using more than 4× compression, and compared the method against PolarQuant, SnapKV, PyramidKV, and KIVI. Google Research stated that TurboQuant was evaluated on long-context benchmarks including LongBench, Needle in a Haystack, ZeroSCROLLS, RULER, and L-Eval using open-source models including Gemma and Mistral. According to a report in Tom's Hardware, Google described the method as reducing KV-cache memory by at least six times and achieving up to an eightfold improvement in attention-logit computation on Nvidia H100 GPUs compared with unquantized 32-bit keys. TurboQuant has also been applied to nearest-neighbor vector search. The original paper reports experiments on DBpedia entity embeddings and GloVe embeddings, comparing TurboQuant with product quantization and other vector-search quantization baselines. == Relationship to other methods == TurboQuant is related to several methods for efficient large language model inference and high-dimensional search: Product quantization – a vector quantization technique widely used for approximate nearest-neighbor search Quantization (machine learning) – reducing the numerical precision of weights, activations, or cached tensors in machine learning models PagedAttention – a memory-management algorithm for LLM serving that reduces fragmentation in the KV cache Johnson–Lindenstrauss lemma – a result in high-dimensional geometry used in random projection methods Lloyd's algorithm – an algorithm for scalar and vector quantization, including k-means-style codebook construction Unlike PagedAttention, which focuses on memory allocation and cache layout, TurboQuant reduces the numerical storage cost of the vectors themselves. Unlike many product-quantization methods, TurboQuant is designed to be data-oblivious and online, avoiding dataset-specific codebook training. == Limitations == The strongest performance claims for TurboQuant come from the original paper and Google Research's own publication. Coverage in technology media has noted that the broader impact of the method will depend on real-world implementation details, workloads, and hardware architectures.

  Read more →
• 

  Randomized rounding

  In computer science and operations research, randomized rounding is a widely used approach for designing and analyzing approximation algorithms. Many combinatorial optimization problems are computationally intractable to solve exactly (to optimality). For such problems, randomized rounding can be used to design fast (polynomial time) approximation algorithms—that is, algorithms that are guaranteed to return an approximately optimal solution given any input. The basic idea of randomized rounding is to convert an optimal solution of a relaxation of the problem into an approximately-optimal solution to the original problem. The resulting algorithm is usually analyzed using the probabilistic method. == Overview == The basic approach has three steps: Formulate the problem to be solved as an integer linear program (ILP). Compute an optimal fractional solution x {\displaystyle x} to the linear programming relaxation (LP) of the ILP. Round the fractional solution x {\displaystyle x} of the LP to an integer solution x ′ {\displaystyle x'} of the ILP. (Although the approach is most commonly applied with linear programs, other kinds of relaxations are sometimes used. For example, see Goemans' and Williamson's semidefinite programming-based Max-Cut approximation algorithm.) In the first step, the challenge is to choose a suitable integer linear program. Familiarity with linear programming, in particular modelling using linear programs and integer linear programs, is required. For many problems, there is a natural integer linear program that works well, such as in the Set Cover example below. (The integer linear program should have a small integrality gap; indeed randomized rounding is often used to prove bounds on integrality gaps.) In the second step, the optimal fractional solution can typically be computed in polynomial time using any standard linear programming algorithm. In the third step, the fractional solution must be converted into an integer solution (and thus a solution to the original problem). This is called rounding the fractional solution. The resulting integer solution should (provably) have cost not much larger than the cost of the fractional solution. This will ensure that the cost of the integer solution is not much larger than the cost of the optimal integer solution. The main technique used to do the third step (rounding) is to use randomization, and then to use probabilistic arguments to bound the increase in cost due to the rounding (following the probabilistic method from combinatorics). Therein, probabilistic arguments are used to show the existence of discrete structures with desired properties. In this context, one uses such arguments to show the following: Given any fractional solution x {\displaystyle x} of the LP, with positive probability the randomized rounding process produces an integer solution x ′ {\displaystyle x'} that approximates x {\displaystyle x} according to some desired criterion. Finally, to make the third step computationally efficient, one either shows that x ′ {\displaystyle x'} approximates x {\displaystyle x} with high probability (so that the step can remain randomized) or one derandomizes the rounding step, typically using the method of conditional probabilities. The latter method converts the randomized rounding process into an efficient deterministic process that is guaranteed to reach a good outcome. == Example: the set cover problem == The following example illustrates how randomized rounding can be used to design an approximation algorithm for the set cover problem. Fix any instance ⟨ c , S ⟩ {\displaystyle \langle c,{\mathcal {S}}\rangle } of set cover over a universe U {\displaystyle {\mathcal {U}}} . === Computing the fractional solution === For step 1, let IP be the standard integer linear program for set cover for this instance. For step 2, let LP be the linear programming relaxation of IP, and compute an optimal solution x ∗ {\displaystyle x^{}} to LP using any standard linear programming algorithm. This takes time polynomial in the input size. The feasible solutions to LP are the vectors x {\displaystyle x} that assign each set s ∈ S {\displaystyle s\in {\mathcal {S}}} a non-negative weight x s {\displaystyle x_{s}} , such that, for each element e ∈ U {\displaystyle e\in {\mathcal {U}}} , x ′ {\displaystyle x'} covers e {\displaystyle e} —the total weight assigned to the sets containing e {\displaystyle e} is at least 1, that is, ∑ s ∋ e x s ≥ 1. {\displaystyle \sum _{s\ni e}x_{s}\geq 1.} The optimal solution x ∗ {\displaystyle x^{}} is a feasible solution whose cost ∑ s ∈ S c ( S ) x s ∗ {\displaystyle \sum _{s\in {\mathcal {S}}}c(S)x_{s}^{}} is as small as possible. Note that any set cover C {\displaystyle {\mathcal {C}}} for S {\displaystyle {\mathcal {S}}} gives a feasible solution x {\displaystyle x} (where x s = 1 {\displaystyle x_{s}=1} for s ∈ C {\displaystyle s\in {\mathcal {C}}} , x s = 0 {\displaystyle x_{s}=0} otherwise). The cost of this C {\displaystyle {\mathcal {C}}} equals the cost of x {\displaystyle x} , that is, ∑ s ∈ C c ( s ) = ∑ s ∈ S c ( s ) x s . {\displaystyle \sum _{s\in {\mathcal {C}}}c(s)=\sum _{s\in {\mathcal {S}}}c(s)x_{s}.} In other words, the linear program LP is a relaxation of the given set-cover problem. Since x ∗ {\displaystyle x^{}} has minimum cost among feasible solutions to the LP, the cost of x ∗ {\displaystyle x^{}} is a lower bound on the cost of the optimal set cover. === Randomized rounding step === In step 3, we must convert the minimum-cost fractional set cover x ∗ {\displaystyle x^{}} into a feasible integer solution x ′ {\displaystyle x'} (corresponding to a true set cover). The rounding step should produce an x ′ {\displaystyle x'} that, with positive probability, has cost within a small factor of the cost of x ∗ {\displaystyle x^{}} .Then (since the cost of x ∗ {\displaystyle x^{}} is a lower bound on the cost of the optimal set cover), the cost of x ′ {\displaystyle x'} will be within a small factor of the optimal cost. As a starting point, consider the most natural rounding scheme: For each set s ∈ S {\displaystyle s\in {\mathcal {S}}} in turn, take x s ′ = 1 {\displaystyle x'_{s}=1} with probability min ( 1 , x s ∗ ) {\displaystyle \min(1,x_{s}^{})} , otherwise take x s ′ = 0 {\displaystyle x'_{s}=0} . With this rounding scheme, the expected cost of the chosen sets is at most ∑ s c ( s ) x s ∗ {\displaystyle \sum _{s}c(s)x_{s}^{}} , the cost of the fractional cover. This is good. Unfortunately the coverage is not good. When the variables x s ∗ {\displaystyle x_{s}^{}} are small, the probability that an element e {\displaystyle e} is not covered is about ∏ s ∋ e 1 − x s ∗ ≈ ∏ s ∋ e exp ⁡ ( − x s ∗ ) = exp ⁡ ( − ∑ s ∋ e x s ∗ ) ≈ exp ⁡ ( − 1 ) . {\displaystyle \prod _{s\ni e}1-x_{s}^{}\approx \prod _{s\ni e}\exp(-x_{s}^{})=\exp {\Big (}-\sum _{s\ni e}x_{s}^{}{\Big )}\approx \exp(-1).} So only a constant fraction of the elements will be covered in expectation. To make x ′ {\displaystyle x'} cover every element with high probability, the standard rounding scheme first scales up the rounding probabilities by an appropriate factor λ > 1 {\displaystyle \lambda >1} . Here is the standard rounding scheme: Fix a parameter λ ≥ 1 {\displaystyle \lambda \geq 1} . For each set s ∈ S {\displaystyle s\in {\mathcal {S}}} in turn, take x s ′ = 1 {\displaystyle x'_{s}=1} with probability min ( λ x s ∗ , 1 ) {\displaystyle \min(\lambda x_{s}^{},1)} , otherwise take x s ′ = 0 {\displaystyle x'_{s}=0} . Scaling the probabilities up by λ {\displaystyle \lambda } increases the expected cost by λ {\displaystyle \lambda } , but makes coverage of all elements likely. The idea is to choose λ {\displaystyle \lambda } as small as possible so that all elements are provably covered with non-zero probability. Here is a detailed analysis. ==== Lemma (approximation guarantee for rounding scheme) ==== Fix λ = ln ⁡ ( 2 | U | ) {\displaystyle \lambda =\ln(2|{\mathcal {U}}|)} . With positive probability, the rounding scheme returns a set cover x ′ {\displaystyle x'} of cost at most 2 ln ⁡ ( 2 | U | ) c ⋅ x ∗ {\displaystyle 2\ln(2|{\mathcal {U}}|)c\cdot x^{}} (and thus of cost O ( log ⁡ | U | ) {\displaystyle O(\log |{\mathcal {U}}|)} times the cost of the optimal set cover). (Note: with care the O ( log ⁡ | U | ) {\displaystyle O(\log |{\mathcal {U}}|)} can be reduced to ln ⁡ ( | U | ) + O ( log ⁡ log ⁡ | U | ) {\displaystyle \ln(|{\mathcal {U}}|)+O(\log \log |{\mathcal {U}}|)} .) ==== Proof ==== The output x ′ {\displaystyle x'} of the random rounding scheme has the desired properties as long as none of the following "bad" events occur: the cost c ⋅ x ′ {\displaystyle c\cdot x'} of x ′ {\displaystyle x'} exceeds 2 λ c ⋅ x ∗ {\displaystyle 2\lambda c\cdot x^{}} , or for some element e {\displaystyle e} , x ′ {\displaystyle x'} fails to cover e {\displaystyle e} . The expectation of each x s ′ {\displaystyle x'_{s}} is at most λ x s ∗ {\displaystyle \lambda x_{s

  Read more →
• 

  Cooperative storage cloud

  A cooperative storage cloud is a decentralized model of networked online storage where data is stored on multiple computers (nodes), hosted by the participants cooperating in the cloud. For the cooperative scheme to be viable, the total storage contributed in aggregate must be at least equal to the amount of storage needed by end users. However, some nodes may contribute less storage and some may contribute more. There may be reward models to compensate the nodes contributing more. Unlike a traditional storage cloud, a cooperative does not directly employ dedicated servers for the actual storage of the data, thereby eliminating the need for a significant dedicated hardware investment. Each node in the cooperative runs specialized software which communicates with a centralized control and orchestration server, thereby allowing the node to both consume and contribute storage space to the cloud. The centralized control and orchestration server requires several orders of magnitude less resources (storage, computing power, and bandwidth) to operate, relative to the overall capacity of the cooperative. == Data security == Files hosted in the cloud are fragmented and encrypted before leaving the local machine. They are then distributed randomly using a load balancing and geo-distribution algorithm to other nodes in the cooperative. Users can add an additional layer of security and reduce storage space by compressing and encrypting files before they are copied to the cloud. == Data redundancy == In order to maintain data integrity and high availability across a relatively unreliable set of computers over a wide area network like the Internet, the source node will add some level of redundancy to each data block. This allows the system to recreate the entire block even if some nodes are temporarily unavailable (due to loss of network connectivity, the machine being powered off or a hardware failure). The most storage and bandwidth efficient forms of redundancy use erasure coding techniques like Reed–Solomon. A simple, less CPU intensive but more expensive form of redundancy is duplicate copies. == Flexible contribution == Due to bandwidth or hardware constraints some nodes may not be able to contribute as much space as they consume in the cloud. On the other hand, nodes with large storage space and limited or no bandwidth constraints may contribute more than they consume, thereby the cooperative can stay in balance.

  Read more →
• 

  Timeline of algorithms

  The following timeline of algorithms outlines the development of algorithms (mainly "mathematical recipes") since their inception. == Antiquity == Before – writing about "recipes" (on cooking, rituals, agriculture and other themes) c. 1700–2000 BC – Egyptians develop earliest known algorithms for multiplying two numbers c. 1600 BC – Babylonians develop earliest known algorithms for factorization and finding square roots c. 300 BC – Euclid's algorithm c. 200 BC – the Sieve of Eratosthenes 263 AD – Gaussian elimination described by Liu Hui == Medieval Period == 628 – Chakravala method described by Brahmagupta c. 820 – Al-Khawarizmi described algorithms for solving linear equations and quadratic equations in his Algebra; the word algorithm comes from his name 825 – Al-Khawarizmi described the algorism, algorithms for using the Hindu–Arabic numeral system, in his treatise On the Calculation with Hindu Numerals, which was translated into Latin as Algoritmi de numero Indorum, where "Algoritmi", the translator's rendition of the author's name gave rise to the word algorithm (Latin algorithmus) with a meaning "calculation method" c. 850 – cryptanalysis and frequency analysis algorithms developed by Al-Kindi (Alkindus) in A Manuscript on Deciphering Cryptographic Messages, which contains algorithms on breaking encryptions and ciphers c. 1025 – Ibn al-Haytham (Alhazen), was the first mathematician to derive the formula for the sum of the fourth powers, and in turn, he develops an algorithm for determining the general formula for the sum of any integral powers c. 1400 – Ahmad al-Qalqashandi gives a list of ciphers in his Subh al-a'sha which include both substitution and transposition, and for the first time, a cipher with multiple substitutions for each plaintext letter; he also gives an exposition on and worked example of cryptanalysis, including the use of tables of letter frequencies and sets of letters which can not occur together in one word == Before 1940 == 1540 – Lodovico Ferrari discovered a method to find the roots of a quartic polynomial 1545 – Gerolamo Cardano published Cardano's method for finding the roots of a cubic polynomial 1614 – John Napier develops method for performing calculations using logarithms 1671 – Newton–Raphson method developed by Isaac Newton 1690 – Newton–Raphson method independently developed by Joseph Raphson 1706 – John Machin develops a quickly converging inverse-tangent series for π and computes π to 100 decimal places 1768 – Leonhard Euler publishes his method for numerical integration of ordinary differential equations in problem 85 of Institutiones calculi integralis 1789 – Jurij Vega improves Machin's formula and computes π to 140 decimal places, 1805 – FFT-like algorithm known by Carl Friedrich Gauss 1842 – Ada Lovelace writes the first algorithm for a computing engine 1903 – A fast Fourier transform algorithm presented by Carle David Tolmé Runge 1918 - Soundex 1926 – Borůvka's algorithm 1926 – Primary decomposition algorithm presented by Grete Hermann 1927 – Hartree–Fock method developed for simulating a quantum many-body system in a stationary state. 1934 – Delaunay triangulation developed by Boris Delaunay 1936 – Turing machine, an abstract machine developed by Alan Turing, with others developed the modern notion of algorithm. == 1940s == 1942 – A fast Fourier transform algorithm developed by G.C. Danielson and Cornelius Lanczos 1945 – Merge sort developed by John von Neumann 1947 – Simplex algorithm developed by George Dantzig == 1950s == 1950 – Hamming codes developed by Richard Hamming 1952 – Huffman coding developed by David A. Huffman 1953 – Simulated annealing introduced by Nicholas Metropolis 1954 – Radix sort computer algorithm developed by Harold H. Seward 1964 – Box–Muller transform for fast generation of normally distributed numbers published by George Edward Pelham Box and Mervin Edgar Muller. Independently pre-discovered by Raymond E. A. C. Paley and Norbert Wiener in 1934. 1956 – Kruskal's algorithm developed by Joseph Kruskal 1956 – Ford–Fulkerson algorithm developed and published by R. Ford Jr. and D. R. Fulkerson 1957 – Prim's algorithm developed by Robert Prim 1957 – Bellman–Ford algorithm developed by Richard E. Bellman and L. R. Ford, Jr. 1959 – Dijkstra's algorithm developed by Edsger Dijkstra 1959 – Shell sort developed by Donald L. Shell 1959 – De Casteljau's algorithm developed by Paul de Casteljau 1959 – QR factorization algorithm developed independently by John G.F. Francis and Vera Kublanovskaya 1959 – Rabin–Scott powerset construction for converting NFA into DFA published by Michael O. Rabin and Dana Scott == 1960s == 1960 – Karatsuba multiplication 1961 – CRC (Cyclic redundancy check) invented by W. Wesley Peterson 1962 – AVL trees 1962 – Quicksort developed by C. A. R. Hoare 1962 – Bresenham's line algorithm developed by Jack E. Bresenham 1962 – Gale–Shapley 'stable-marriage' algorithm developed by David Gale and Lloyd Shapley 1964 – Heapsort developed by J. W. J. Williams 1964 – multigrid methods first proposed by R. P. Fedorenko 1965 – Cooley–Tukey algorithm rediscovered by James Cooley and John Tukey 1965 – Levenshtein distance developed by Vladimir Levenshtein 1965 – Cocke–Younger–Kasami (CYK) algorithm independently developed by Tadao Kasami 1965 – Buchberger's algorithm for computing Gröbner bases developed by Bruno Buchberger 1965 – LR parsers invented by Donald Knuth 1966 – Dantzig algorithm for shortest path in a graph with negative edges 1967 – Viterbi algorithm proposed by Andrew Viterbi 1967 – Cocke–Younger–Kasami (CYK) algorithm independently developed by Daniel H. Younger 1968 – A graph search algorithm described by Peter Hart, Nils Nilsson, and Bertram Raphael 1968 – Risch algorithm for indefinite integration developed by Robert Henry Risch 1969 – Strassen algorithm for matrix multiplication developed by Volker Strassen == 1970s == 1970 – Dinic's algorithm for computing maximum flow in a flow network by Yefim (Chaim) A. Dinitz 1970 – Knuth–Bendix completion algorithm developed by Donald Knuth and Peter B. Bendix 1970 – BFGS method of the quasi-Newton class 1970 – Needleman–Wunsch algorithm published by Saul B. Needleman and Christian D. Wunsch 1972 – Edmonds–Karp algorithm published by Jack Edmonds and Richard Karp, essentially identical to Dinic's algorithm from 1970 1972 – Graham scan developed by Ronald Graham 1972 – Red–black trees and B-trees discovered 1973 – RSA encryption algorithm discovered by Clifford Cocks 1973 – Jarvis march algorithm developed by R. A. Jarvis 1973 – Hopcroft–Karp algorithm developed by John Hopcroft and Richard Karp 1974 – Pollard's p − 1 algorithm developed by John Pollard 1974 – Quadtree developed by Raphael Finkel and J.L. Bentley 1975 – Genetic algorithms popularized by John Holland 1975 – Pollard's rho algorithm developed by John Pollard 1975 – Aho–Corasick string matching algorithm developed by Alfred V. Aho and Margaret J. Corasick 1975 – Cylindrical algebraic decomposition developed by George E. Collins 1976 – Salamin–Brent algorithm independently discovered by Eugene Salamin and Richard Brent 1976 – Knuth–Morris–Pratt algorithm developed by Donald Knuth and Vaughan Pratt and independently by J. H. Morris 1977 – Boyer–Moore string-search algorithm for searching the occurrence of a string into another string. 1977 – RSA encryption algorithm rediscovered by Ron Rivest, Adi Shamir, and Len Adleman 1977 – LZ77 algorithm developed by Abraham Lempel and Jacob Ziv 1977 – multigrid methods developed independently by Achi Brandt and Wolfgang Hackbusch 1978 – LZ78 algorithm developed from LZ77 by Abraham Lempel and Jacob Ziv 1978 – Bruun's algorithm proposed for powers of two by Georg Bruun 1979 – Khachiyan's ellipsoid method developed by Leonid Khachiyan 1979 – ID3 decision tree algorithm developed by Ross Quinlan == 1980s == 1980 – Brent's Algorithm for cycle detection Richard P. Brendt 1981 – Quadratic sieve developed by Carl Pomerance 1981 – Smith–Waterman algorithm developed by Temple F. Smith and Michael S. Waterman 1983 – Simulated annealing developed by S. Kirkpatrick, C. D. Gelatt and M. P. Vecchi 1983 – Classification and regression tree (CART) algorithm developed by Leo Breiman, et al. 1984 – LZW algorithm developed from LZ78 by Terry Welch 1984 – Karmarkar's interior-point algorithm developed by Narendra Karmarkar 1984 – ACORN PRNG discovered by Roy Wikramaratna and used privately 1985 – Simulated annealing independently developed by V. Cerny 1985 – Car–Parrinello molecular dynamics developed by Roberto Car and Michele Parrinello 1985 – Splay trees discovered by Sleator and Tarjan 1986 – Blum Blum Shub proposed by L. Blum, M. Blum, and M. Shub 1986 – Push relabel maximum flow algorithm by Andrew Goldberg and Robert Tarjan 1986 – Barnes–Hut tree method developed by Josh Barnes and Piet Hut for fast approximate simulation of n-body problems 1987 – Fast multipole method developed by Leslie Greengard and Vladimir

  Read more →
• 

  Ontology merging

  Ontology merging defines the act of bringing together two conceptually divergent ontologies or the instance data associated to two ontologies. This is similar to work in database merging (schema matching). This merging process can be performed in a number of ways, manually, semi automatically, or automatically. Manual ontology merging although ideal is extremely labour-intensive and current research attempts to find semi or entirely automated techniques to merge ontologies. These techniques are statistically driven often taking into account similarity of concepts and raw similarity of instances through textual string metrics and semantic knowledge. These techniques are similar to those used in information integration employing string metrics from open source similarity libraries.

  Read more →
• 

  Wearable technology

  Wearable technology is a category of small electronic and mobile devices with wireless communications capability designed to be worn on the human body and are incorporated into gadgets, accessories, or clothes. Common types of wearable technology include smartwatches, fitness trackers, and smartglasses. Wearable electronic devices are often close to or on the surface of the skin, where they detect, analyze, and transmit information such as vital signs, and/or ambient data and which allow in some cases immediate biofeedback to the wearer. Wearable devices collect vast amounts of data from users making use of different behavioral and physiological sensors, which monitor their health status and activity levels. Wrist-worn devices include smartwatches with a touchscreen display, while wristbands are mainly used for fitness tracking but do not contain a touchscreen display. Wearable devices such as activity trackers are an example of the Internet of things, since "things" such as electronics, software, sensors, and connectivity are effectors that enable objects to exchange data (including data quality) through the internet with a manufacturer, operator, and/or other connected devices, without requiring human intervention. Wearable technology offers a wide range of possible uses, from communication and entertainment to improving health and fitness, however, there are worries about privacy and security because wearable devices have the ability to collect personal data. Wearable technology has a variety of use cases which is growing as the technology is developed and the market expands. It can be used to encourage individuals to be more active and improve their lifestyle choices. Healthy behavior is encouraged by tracking activity levels and providing useful feedback to enable goal setting. This can be shared with interested stakeholders such as healthcare providers. Wearables are popular in consumer electronics, most commonly in the form factors of smartwatches, smart rings, and implants. Apart from commercial uses, wearable technology is being incorporated into navigation systems, advanced textiles (e-textiles), and healthcare. As wearable technology is being proposed for use in critical applications, like other technology, it is vetted for its reliability and security properties. == History == In the 1500s, German inventor Peter Henlein (1485–1542) created small watches that were worn as necklaces. A century later, pocket watches grew in popularity as waistcoats became fashionable for men. Wristwatches were created in the late 1600s but were worn mostly by women as bracelets. Pedometers were developed around the same time as pocket watches. The concept of a pedometer was described by Leonardo da Vinci around 1500, and the Germanic National Museum in Nuremberg has a pedometer in its collection from 1590. In the late 1800s, the first wearable hearing aids were introduced. In 1904, aviator Alberto Santos-Dumont pioneered the modern use of the wristwatch. In 1949, American biophysicist Norman Holter invented the very first health monitoring device. His invention, the Holter monitor, was groundbreaking as one of the first wearable devices capable of tracking vital health data outside of a clinical setting. In the 1970s, calculator watches became available, reaching the peak of their popularity in the 1980s. From the early 2000s, wearable cameras were being used as part of a growing sousveillance movement. Expectations, operations, usage and concerns about wearable technology was floated on the first International Conference on Wearable Computing. In 2008, Ilya Fridman incorporated a hidden Bluetooth microphone into a pair of earrings. Big tech companies such as Apple, Samsung, and Fitbit have expanded on this idea by interfacing with smartphones and personal computer software to collect a wide variety of data. Wearable devices include dedicated health monitors, fitness bands, and smartwatches. In 2010, Fitbit released its first step counter. Wearable technology which tracks information such as walking and heart rate is part of the quantified self movement. In 2013, McLear, also known as NFC Ring, released a "smart ring". The smart ring could make bitcoin payments, unlock other devices, and transfer personally identifying information, and also had other features. In 2013, one of the first widely available smartwatches was the Samsung Galaxy Gear. Apple followed in 2015 with the Apple Watch. === Prototypes === From 1991 to 1997, Rosalind Picard and her students, Steve Mann and Jennifer Healey, at the MIT Media Lab designed, built, and demonstrated data collection and decision making from "Smart Clothes" that monitored continuous physiological data from the wearer. These "smart clothes", "smart underwear", "smart shoes", and smart jewellery collected data that related to affective state and contained or controlled physiological sensors and environmental sensors like cameras and other devices. At the same time, also at the MIT Media Lab, Thad Starner and Alex "Sandy" Pentland develop augmented reality. In 1997, their smartglass prototype is featured on 60 Minutes and enables rapid web search and instant messaging. Though the prototype's glasses are nearly as streamlined as modern smartglasses, the processor was a computer worn in a backpack – the most lightweight solution available at the time. In 2009, Sony Ericsson teamed up with the London College of Fashion for a contest to design digital clothing. The winner was a cocktail dress with Bluetooth technology making it light up when a call is received. Zach "Hoeken" Smith of MakerBot fame made keyboard pants during a "Fashion Hacking" workshop at a New York City creative collective. The Tyndall National Institute in Ireland developed a "remote non-intrusive patient monitoring" platform which was used to evaluate the quality of the data generated by the patient sensors and how the end users may adopt to the technology. More recently, London-based fashion company CuteCircuit created costumes for singer Katy Perry featuring LED lighting so that the outfits would change color both during stage shows and appearances on the red carpet such as the dress Katy Perry wore in 2010 at the MET Gala in NYC. In 2012, CuteCircuit created the world's first dress to feature Tweets, as worn by singer Nicole Scherzinger. In 2010, McLear, also known as NFC Ring, developed prototypes of its "smart ring" devices, before a Kickstarter fundraising in 2013. In 2014, graduate students from the Tisch School of Arts in New York designed a hoodie that sent pre-programmed text messages triggered by gesture movements. Around the same time, prototypes for digital eyewear with heads up display (HUD) began to appear. The US military employs headgear with displays for soldiers using a technology called holographic optics. In 2010, Google started developing prototypes of its optical head-mounted display Google Glass, which went into customer beta in March 2013. == Usage == In the consumer space, sales of smart wristbands (aka activity trackers such as the Jawbone UP and Fitbit Flex) started accelerating in 2013. One in five American adults have a wearable device, according to the 2014 PriceWaterhouseCoopers Wearable Future Report. As of 2009, decreasing cost of processing power and other components was facilitating widespread adoption and availability. In professional sports, wearable technology has applications in monitoring and real-time feedback for athletes. Examples of wearable technology in sport include accelerometers, pedometers, and GPS's which can be used to measure an athlete's energy expenditure and movement pattern. In cybersecurity and financial technology, secure wearable devices have captured part of the physical security key market. McLear, also known as NFC Ring, and VivoKey developed products with one-time pass secure access control. In health informatics, wearable devices have enabled better capturing of human health statistics for data driven analysis. This has facilitated data-driven machine learning algorithms to analyse the health condition of users. In business, wearable technology helps managers easily supervise employees by knowing their locations and what they are currently doing. Employees working in a warehouse also have increased safety when working around chemicals or lifting something. Smart helmets are employee safety wearables that have vibration sensors that can alert employees of possible danger in their environment. == Wearable technology and health == Wearable technology is often used to monitor a user's health. Given that such a device is in close contact with the user, it can easily collect data. It started as soon as 1980 where first wireless ECG was invented. In the last decades, there has been substantial growth in research of e.g. textile-based, tattoo, patch, and contact lenses as well as circulation of a notion of "quantified self", transhumanism-related ideas, and growth of life ex

  Read more →
• 

  Avid Symphony

  Avid Symphony is non-linear editing software aimed at professionals in the film and television industry. It is available for Microsoft Windows PCs and Apple Macintosh platforms. Symphony is Avid's high end SD/HD finishing platform for long form work, such as documentary and episodic TV. Its interface is based on the same look and feature set as the Media Composer and Xpress systems, but contains the highest level of features and resolution including secondary color correction, uncompressed HD, and higher real-time performance. == Release history == Symphony is the software component of a tightly integrated package that includes specific hardware audio/video interfaces, storage, and the computer, also sold by Avid. Its release history is therefore tightly related to the release of new Avid interface hardware: Symphony was introduced to the market in 1998. It was based on Avid's Meridien hardware, supporting SD only, and was available first only for the PC and later for the Macintosh platforms. Its last release was 5.0.5 which supported Windows 2000 and Mac OS X v10.2. The next major upgrade was Symphony Nitris in 2005, with a redesigned software and integration with the Nitris DNA hardware (PCI-X). It supported 8 bit and 10 bit SD and HD resolutions in both compressed and uncompressed forms, the MXF format and DNxHD codec, and ran only on Windows PC platforms. Symphony Nitris DX, released in 2008, added support for a range of HD codecs, including HDV, XDCAM-HD, DVCPRO HD, and AVC-I, and brought back Mac OS support for OS X 10.5, as well as Windows Vista. Since the introduction of Symphony 6, it can be used in software-only mode (where a Nitris or Nitris DX BOB used to be required), and at the same time, like Media Composer, Symphony was opened up with "Open I/O", allowing users to have Symphony use their third party hardware from companies like AJA, Matrox, BlueFish, Blackmagic Design and MOTU. The last remaining features that differentiate it from Media Composer are Advanced Color Correction (channels, secondary color correction,), Relational Color Correction (corrections based on common clip name, tape name, program track) and Universal HD Mastering (only with Nitris DX hardware). The latter allows cross-conversions of 23.976p or 24p projects sequences to most any other format during Digital Cut. In 2013, Avid announced it would no longer offer Symphony a standalone product. Starting version 7, Symphony will be sold as an option to Media Composer. This optional package (sold at a premium) will contain all the traditional Symphony-only features to any Media Composer install. == Use in movies == The Celibacy, Director: Horacio Bocaranda Avid Media Composer 6 and Avid Symphony 6 Nitris DX American Hardcore, Director: Paul Rachman Avid Xpress Pro and Symphony Summercamp!, Director: Spike Lee Avid Xpress Pro and Symphony When the Levees Broke Avid Media Composer and Symphony Nitris Superman Returns Edited with Mac-based Film Composer XL, but HD screenings prepped with Symphony

  Read more →
• 

  Archetype (information science)

  In the field of informatics, an archetype is a formal re-usable model of a domain concept. Traditionally, the term archetype is used in psychology to mean an idealized model of a person, personality or behaviour (see Archetype). The usage of the term in informatics is derived from this traditional meaning, but applied to domain modelling instead. An archetype is defined by the OpenEHR Foundation (for health informatics) as follows: An archetype is a computable expression of a domain content model in the form of structured constraint statements, based on some reference model. openEHR archetypes are based on the openEHR reference model. Archetypes are all expressed in the same formalism. In general, they are defined for wide re-use, however, they can be specialized to include local particularities. They can accommodate any number of natural languages and terminologies. == Formal specifications == The modern archetype formalism is specified and maintained by the openEHR Foundation, and although originally developed for the health IT domain, is completely domain-independent, and has been used in geospatial modelling, telecommunications, and defence. The archetype formalism consists of a number of specifications including: 'ADL 1.4': original release of Archetype Definition Language (ADL) and Archetype Object Model (AOM); widely implemented in health IT domain; 'ADL 2': modern release of Archetype Definition Language (ADL), Archetype Object Model (AOM), Archetype Identification specification and Archetype Technology Overview. The Archetype Technology Overview provides a short technical overview of the archetype formalism useful for new users. The ADL/AOM 1.4 specifications were provided to ISO TC 215 in 2008 by the openEHR Foundation and became the ISO 13606-2 standard, extant until 2019. ISO TC 215 accepted the AOM 2 specification as the basis for a revision of this standard, which was issued in 2019. In late 2015, the Object Management Group (OMG) accepted an RfP entitled 'Archetype Modeling Language (AML)' as a new candidate standard. This specification is a form of ADL re-engineered as a UML profile so as to enable archetype modelling to be supported within UML tools. == Tools == A number of tools area available for working with archetypes. Most are listed on the openEHR modelling tools page. They include: ADL Designer, a modern AOM2-based web editing application Archetype Editor, an original desktop clinical modelling tool Template Designer, an original desktop clinical templating tool LinkEHR, an archetype and data integration tool ADL Workbench, reference compiler and visualiser tool == Example ==

  Read more →
• 

  Evidence-based library and information practice

  Evidence-based library and information practice (EBLIP) or evidence-based librarianship (EBL) is the use of evidence-based practices (EBP) in the field of library and information science (LIS). This means that all practical decisions made within LIS should 1) be based on research studies and 2) that these research studies are selected and interpreted according to some specific norms characteristic for EBP. Typically such norms disregard theoretical studies and qualitative studies and consider quantitative studies according to a narrow set of criteria of what counts as evidence. If such a narrow set of methodological criteria are not applied, it is better instead to speak of research based library and information practice. == Characteristics == Evidence-based practice in general has been characterised as a positivist approach; EBLIP is therefore also a positivist approach to LIS. As such, EBLIP is an approach in contrast to other approaches to LIS. The use of statistical approaches known as meta-analysis to conclude what evidence has been reported in the literature is one among other methods which is typical for the evidence-based approach. In 2002, Booth noted the three schools of EBILP had some commonalities, including the context of day-to-day decision-making, an emphasis on improving the quality of professional practice, a pragmatic focus on the 'best available evidence', incorporation of the user perspective, the acceptance of a broad range of quantitative and qualitative research designs, and access, either first-hand or second-hand, to the (process of) evidence-based practice and its products. He added one more, that EBILP is concerned with getting the best value for money. == The role of library and information science in EBP == Evidence-based practice in general is based on a very thorough search of the scientific literature and a very thorough selection and analysis of the retrieved literature. A close familiarity with database searching is needed, and library and information professionals have important roles to play in this respect. Therefore LIS professionals should be well suited to help professionals in other disciplines doing EBP. EBLIP is the application of this approach on LIS itself. It should be mentioned, however, that EBP started in medicine as evidence-based medicine (EBM) from which it spread to other fields. Only slowly and to a limited extent has EBP moved on to LIS. The EBLIP process can be applied to a variety of scenarios in LIS, including customer service, collection development, library management and information literacy instruction. In general, quantitative methods are used in LIS research. A 2010 study revealed five categories that capture the different ways library and information professionals experience evidence-based practice: Evidence-based practice is experienced as irrelevant; Evidence-based practice is experienced as learning from published research; Evidence-based practice is experienced as service improvement; Evidence-based practice is experienced as a way of being; Evidence-based practice is experienced as a weapon.

  Read more →