Outlook on the web (formerly Outlook Web App and Outlook Web Access) is a personal information manager web app from Microsoft. It is a web-based version of Microsoft Outlook, and is included in Exchange Server and Exchange Online (a component of Microsoft 365). It can be freely accessed from any web browser whether inside or outside an organization's network, and includes a web email client, a calendar tool, a contact manager, and a task manager. It also includes add-in integration, Skype on the web, and alerts as well as unified themes that span across all the web apps. == Purpose == Outlook on the web is available to Microsoft 365 (formerly Office 365) and Exchange Online subscribers, and is included with the on-premises Exchange Server, to enable users to connect to their email accounts via a web browser, without requiring the installation of Microsoft Outlook or other email clients. In case of Exchange Server, it is hosted on a local intranet and requires a network connection to the Exchange Server for users to work with e-mail, address book, calendars and task. The Exchange Online version, which can be bought either independently or through Office 365 licensing program, is hosted on Microsoft servers on the World Wide Web. == History == Outlook Web Access was created in 1995 by Microsoft Program Manager Thom McCann on the Exchange Server team. An early working version was demonstrated by Microsoft Vice President Paul Maritz at Microsoft's famous Internet summit in Seattle on December 27, 1995. The first customer version was shipped as part of the Exchange Server 5.0 release in early 1997. The first component to allow client-side scripts to issue HTTP requests (XMLHTTP) was originally written by the Outlook Web Access team. It soon became a part of Internet Explorer 5. Renamed XMLHttpRequest and standardized by the World Wide Web Consortium, it has since become one of the cornerstones of the Ajax technology used to build advanced web apps. Outlook Web Access was later renamed Outlook Web App in 2010. An update on August 4, 2015, renamed OWA to "Outlook on the web", often referred to in brief as simply "Outlook". == Components == === Mail === Mail is the webmail component of Outlook on the web. The default view is a three column view with folders and groups on the left, an email message list in the middle, and the selected message on the right. With the 2015 update, Microsoft introduced the ability to pin, sweep and archive messages, and undo the last action, as well as richer image editing features. It can connect to other services such as GitHub and Twitter through Office 365 Connectors. Actionable Messages in emails allows a user to complete a task from within the email, such as retweeting a Tweet on Twitter or setting a meeting date on a calendar. Outlook on the web supports S/MIME and includes features for managing calendars, contacts, tasks, documents (used with SharePoint or Office Web Apps), and other mailbox content. In the Exchange 2007 release, Outlook on the web (still called Outlook Web App at the time) also offers read-only access to documents stored in SharePoint sites and network UNC shares. === Calendar === Calendar is the calendaring component of Outlook on the web. With the update, Microsoft added a weather forecast directly in the Calendar, as well as icons (or "charms") as visual cues for an event. In addition, email reminders came to all events, and a special Birthday and Holiday event calendars are created automatically. Calendars can be shared and there are multiple views such as day, week, month, and today. Another view is work week which includes Mondays through Fridays in the calendar view. Calendar's "Board View" feature allows for a customizable calendar with widgets such as Goal, Calendar, Tasks and Tips. Calendar details can be added with HTML and rich-text editing, and files can be attached to calendar events and appointments. === People === People is the contact manager component of Outlook on the web. A user can search and edit existing contacts, as well as create new ones. Contacts can be placed into folders and duplicate contacts can be linked from multiple sources such as LinkedIn or Twitter. In Outlook Mail, a contact can be created by clicking on an email address sender, which pulls down a contact card with an add button to add to Outlook People. Contacts can be imported as well as placed into a list that can be utilized when composing an email in Outlook Mail. People can also sync with friends and connections lists on LinkedIn, Facebook, and Twitter. === To Do === To Do was originally launched as Tasks for Outlook Web App. Microsoft was slowly rolling out a preview of Tasks to its consumer-based Outlook.com service that in May 2015, was announced to be moving to the Office 365 infrastructure. It was initially a part of Calendar as a view. Microsoft has separated the services into its own web app in Outlook on the web. In a post on the Office Blogs in 2015, Microsoft announced that Outlook Web App would be renamed Outlook on the web and that Tasks would move under that brand. A user can create tasks, put them into categories, and move them to another folder. A feature added was the ability to set due days and sort and filter the tasks according to those criteria. The app provides the user with fields such as subject, start and end dates, percent complete, priority, and how much work was put into each task. Rich editing features like bold, italic, underline, numbering, and bullet points were also introduced. Tasks can be edited and categorized according to how the user wishes them to be sorted. == Removed features == Outlook on the web has had two interfaces available: one with a complete feature set (known as Premium) and one with reduced functionality (known as Light or sometimes Lite). Prior to Exchange 2010, the Premium client required Internet Explorer. Exchange 2000 and 2003 require Internet Explorer 5 and later, and Exchange 2007 requires Internet Explorer 6 and later. Exchange 2010 supports a wider range of web browsers: Internet Explorer 7 or later, Firefox 3.01 or later, Chrome, or Safari 3.1 or later. However, Exchange 2010 restricts its Firefox and Safari support to macOS and Linux. In Exchange 2013, these browser restrictions were lifted. In Exchange 2010 and earlier, the Light user interface is rendered for browsers other than Internet Explorer. The basic interface did not support search on Exchange Server 2003. In Exchange Server 2007, the Light interface supported searching mail items; managing contacts and the calendar was also improved. The 2010 version can connect to an external email account. The ability to add new accounts to Outlook on the web using the Connected accounts feature was removed in September 2018 and all connected accounts stopped synchronizing email the following month.
Gollum browser
Gollum browser is a discontinued web browser for accessing Wikipedia. Since 2017, Gollum is no longer accessible online. Gollum is designed to browse Wikipedia in an easier way than directly using the web browser. Links external to Wikipedia are opened in the user's regular browser. Gollum is opened from a regular browser and makes a window that puts the Wikipedia search bar on the toolbar. Gollum was created by Harald Hanek in 2005 using PHP and Ajax. According to one blogger, Gollum provides a way to bypass censorship of Wikipedia in China. == Languages == Though the website is available only in English and German, Gollum's GUI is available in more than 32 languages and can browse nearly 50 Wikipedia editions. === Gollum's GUI === === Browsable Wikipedia editions ===
Kolmogorov–Arnold Networks
Kolmogorov–Arnold Networks (KANs) are a type of artificial neural network architecture inspired by the Kolmogorov–Arnold representation theorem, also known as the superposition theorem. Unlike traditional multilayer perceptrons (MLPs), which rely on fixed activation functions and linear weights, KANs replace each weight with a learnable univariate function, often represented using splines. == History == KANs (Kolmogorov–Arnold Networks) were proposed by Liu et al. (2024) as a generalization of the Kolmogorov–Arnold representation theorem (KART), aiming to outperform MLPs in small-scale AI and scientific tasks. Before KANs, numerous studies explored KART's connections to neural networks or used it as a basis for designing new network architectures. In the 1980s and 1990s, early research applied KART to neural network design. Kůrková et al. (1992), Hecht-Nielsen (1987), and Nees (1994) established theoretical foundations for multilayer networks based on KART. Igelnik et al. (2003) introduced the Kolmogorov Spline Network using cubic splines to model complex functions. Sprecher (1996, 1997) introduced numerical methods for building network layers, while Nakamura et al. (1993) created activation functions with guaranteed approximation accuracy. These works linked KART's theoretical potential with practical neural network implementation. KART has also been used in other computational and theoretical fields. Coppejans (2004) developed nonparametric regression estimators using B-splines, Bryant (2008) applied it to high-dimensional image tasks, Liu (2015) investigated theoretical applications in optimal transport and image encryption, and more recently, Polar and Poluektov (2021) used Urysohn operators for efficient KART construction, while Fakhoury et al. (2022) introduced ExSpliNet, integrating KART with probabilistic trees and multivariate B-splines for improved function approximation. == Architecture == KANs are based on the Kolmogorov–Arnold representation theorem, which was linked to the 13th Hilbert problem. Given x = ( x 1 , x 2 , … , x n ) {\displaystyle x=(x_{1},x_{2},\dots ,x_{n})} consisting of n variables, a multivariate continuous function f ( x ) {\displaystyle f(x)} can be represented as: f ( x ) = f ( x 1 , … , x n ) = ∑ q = 1 2 n + 1 Φ q ( ∑ p = 1 n φ q , p ( x p ) ) {\displaystyle f(x)=f(x_{1},\dots ,x_{n})=\sum _{q=1}^{2n+1}\Phi _{q}\left(\sum _{p=1}^{n}\varphi _{q,p}(x_{p})\right)} (1) This formulation contains two nested summations: an outer and an inner sum. The outer sum ∑ q = 1 2 n + 1 {\displaystyle \sum _{q=1}^{2n+1}} aggregates 2 n + 1 {\displaystyle 2n+1} terms, each involving a function Φ q : R → R {\displaystyle \Phi _{q}:\mathbb {R} \to \mathbb {R} } . The inner sum ∑ p = 1 n {\displaystyle \sum _{p=1}^{n}} computes n terms for each q, where each term φ q , p : [ 0 , 1 ] → R {\displaystyle \varphi _{q,p}:[0,1]\to \mathbb {R} } is a continuous function of the single variable x p {\displaystyle x_{p}} . The inner continuous functions φ q , p {\displaystyle \varphi _{q,p}} are universal, independent of f {\displaystyle f} , while the outer functions Φ q {\displaystyle \Phi _{q}} depend on the specific function f {\displaystyle f} being represented. The representation (1) holds for all multivariate functions f {\displaystyle f} as proved in . If f {\displaystyle f} is continuous, then the outer functions Φ q {\displaystyle \Phi _{q}} are continuous; if f {\displaystyle f} is discontinuous, then the corresponding Φ q {\displaystyle \Phi _{q}} are generally discontinuous, while the inner functions φ q , p {\displaystyle \varphi _{q,p}} remain the same universal functions. Liu et al. proposed the name KAN. A general KAN network consisting of L layers takes x to generate the output as: K A N ( x ) = ( Φ L − 1 ∘ Φ L − 2 ∘ ⋯ ∘ Φ 1 ∘ Φ 0 ) x {\displaystyle \mathrm {KAN} (x)=(\Phi ^{L-1}\circ \Phi ^{L-2}\circ \cdots \circ \Phi ^{1}\circ \Phi ^{0})x} (3) Here, Φ l {\displaystyle \Phi ^{l}} is the function matrix of the l-th KAN layer or a set of pre-activations. Let i denote the neuron of the l-th layer and j the neuron of the (l+1)-th layer. The activation function φ j , i l {\displaystyle \varphi _{j,i}^{l}} connects (l, i) to (l+1, j): φ j , i l , l = 0 , … , L − 1 , i = 1 , … , n l , j = 1 , … , n l + 1 {\displaystyle \varphi _{j,i}^{l},\quad l=0,\dots ,L-1,\;i=1,\dots ,n_{l},\;j=1,\dots ,n_{l+1}} (4) where nl is the number of nodes of the l-th layer. Thus, the function matrix Φ l {\displaystyle \Phi ^{l}} can be represented as an n l + 1 × n l {\displaystyle n_{l+1}\times n_{l}} matrix of activations: x l + 1 = ( φ 1 , 1 l ( ⋅ ) φ 1 , 2 l ( ⋅ ) ⋯ φ 1 , n l l ( ⋅ ) φ 2 , 1 l ( ⋅ ) φ 2 , 2 l ( ⋅ ) ⋯ φ 2 , n l l ( ⋅ ) ⋮ ⋮ ⋱ ⋮ φ n l + 1 , 1 l ( ⋅ ) φ n l + 1 , 2 l ( ⋅ ) ⋯ φ n l + 1 , n l l ( ⋅ ) ) x l {\displaystyle x^{l+1}={\begin{pmatrix}\varphi _{1,1}^{l}(\cdot )&\varphi _{1,2}^{l}(\cdot )&\cdots &\varphi _{1,n_{l}}^{l}(\cdot )\\\varphi _{2,1}^{l}(\cdot )&\varphi _{2,2}^{l}(\cdot )&\cdots &\varphi _{2,n_{l}}^{l}(\cdot )\\\vdots &\vdots &\ddots &\vdots \\\varphi _{n_{l+1},1}^{l}(\cdot )&\varphi _{n_{l+1},2}^{l}(\cdot )&\cdots &\varphi _{n_{l+1},n_{l}}^{l}(\cdot )\end{pmatrix}}x^{l}} == Implementations == To make the KAN layers optimizable, the inner function is formed by the combination of spline and basic functions as the formula: φ ( x ) = w b b ( x ) + w s spline ( x ) {\displaystyle \varphi (x)=w_{b}\,b(x)+w_{s}\,{\text{spline}}(x)} where b ( x ) {\displaystyle b(x)} is the basic function, usually defined as s i l u ( x ) = x / ( 1 + e x ) {\displaystyle silu(x)=x/(1+e^{x})} and w b {\displaystyle w_{b}} is the base weight matrix. Also, w s {\displaystyle w_{s}} is the spline weight matrix and spline ( x ) {\displaystyle {\text{spline}}(x)} is the spline function. The spline function can be a sum of B-splines. spline ( x ) = ∑ i c i B i ( x ) {\displaystyle {\text{spline}}(x)=\sum _{i}c_{i}B_{i}(x)} Many studies suggested to use other polynomial and curve functions instead of B-spline to create new KAN variants. == Functions used == The choice of functional basis strongly influences the performance of KANs. Common function families include: B-splines: Provide locality, smoothness, and interpretability; they are the most widely used in current implementations. RBFs (include Gaussian RBFs): Capture localized features in data and are effective in approximating functions with non-linear or clustered structures. Chebyshev polynomials: Offer efficient approximation with minimized error in the maximum norm, making them useful for stable function representation. Rational function: Useful for approximating functions with singularities or sharp variations, as they can model asymptotic behavior better than polynomials. Fourier series: Capture periodic patterns effectively and are particularly useful in domains such as physics-informed machine learning. Wavelet functions (DoG, Mexican hat, Morlet, and Shannon): Used for feature extraction as they can capture both high-frequency and low-frequency data components. Piecewise linear functions: Provide efficient approximation for multivariate functions in KANs. == Usage == In some modern neural architectures like convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Transformers, KANs are typically used as drop-in substitutes for MLP layers. Despite KANs' general-purpose design, researchers have created and used them for a number of tasks: Scientific machine learning (SciML): Function fitting, partial differential equations (PDEs) and physical/mathematical laws. Continual learning: KANs better preserve previously learned information during incremental updates, avoiding catastrophic forgetting due to the locality of spline adjustments. Graph neural networks: Extensions such as Kolmogorov–Arnold Graph Neural Networks (KA-GNNs) integrate KAN modules into message-passing architectures, showing improvements in molecular property prediction tasks. Sensor data processing: Kolmogorov–Arnold Networks (KANs) have recently been applied to sensor data processing due to their ability to model complex nonlinear relationships with relatively few parameters and improved interpretability compared to conventional multilayer perceptrons. Applications include industrial soft sensors, biomedical signal analysis, remote sensing, and environmental monitoring systems. == Drawbacks == KANs can be computationally intensive and require a large number of parameters due to their use of polynomial functions to capture data.
Data-driven model
Data-driven models are a class of computational models that primarily rely on historical data collected throughout a system's or process' lifetime to establish relationships between input, internal, and output variables. Commonly found in numerous articles and publications, data-driven models have evolved from earlier statistical models, overcoming limitations posed by strict assumptions about probability distributions. These models have gained prominence across various fields, particularly in the era of big data, artificial intelligence, and machine learning, where they offer valuable insights and predictions based on the available data. == Background == These models have evolved from earlier statistical models, which were based on certain assumptions about probability distributions that often proved to be overly restrictive. The emergence of data-driven models in the 1950s and 1960s coincided with the development of digital computers, advancements in artificial intelligence research, and the introduction of new approaches in non-behavioural modelling, such as pattern recognition and automatic classification. == Key Concepts == Data-driven models encompass a wide range of techniques and methodologies that aim to intelligently process and analyse large datasets. Examples include fuzzy logic, fuzzy and rough sets for handling uncertainty, neural networks for approximating functions, global optimization and evolutionary computing, statistical learning theory, and Bayesian methods. These models have found applications in various fields, including economics, customer relations management, financial services, medicine, and the military, among others. Machine learning, a subfield of artificial intelligence, is closely related to data-driven modelling as it also focuses on using historical data to create models that can make predictions and identify patterns. In fact, many data-driven models incorporate machine learning techniques, such as regression, classification, and clustering algorithms, to process and analyse data. In recent years, the concept of data-driven models has gained considerable attention in the field of water resources, with numerous applications, academic courses, and scientific publications using the term as a generalization for models that rely on data rather than physics. This classification has been featured in various publications and has even spurred the development of hybrid models in the past decade. Hybrid models attempt to quantify the degree of physically based information used in hydrological models and determine whether the process of building the model is primarily driven by physics or purely data-based. As a result, data-driven models have become an essential topic of discussion and exploration within water resources management and research. The term "data-driven modelling" (DDM) refers to the overarching paradigm of using historical data in conjunction with advanced computational techniques, including machine learning and artificial intelligence, to create models that can reveal underlying trends, patterns, and, in some cases, make predictions Data-driven models can be built with or without detailed knowledge of the underlying processes governing the system behavior, which makes them particularly useful when such knowledge is missing or fragmented.
And–or tree
An and–or tree is a graphical representation of the reduction of problems (or goals) to conjunctions and disjunctions of subproblems (or subgoals). == Example == The and–or tree: represents the search space for solving the problem P, using the goal-reduction methods: P if Q and R P if S Q if T Q if U == Definitions == Given an initial problem P0 and set of problem solving methods of the form: P if P1 and … and Pn the associated and–or tree is a set of labelled nodes such that: The root of the tree is a node labelled by P0. For every node N labelled by a problem or sub-problem P and for every method of the form P if P1 and ... and Pn, there exists a set of children nodes N1, ..., Nn of the node N, such that each node Ni is labelled by Pi. The nodes are conjoined by an arc, to distinguish them from children of N that might be associated with other methods. A node N, labelled by a problem P, is a success node if there is a method of the form P if nothing (i.e., P is a "fact"). The node is a failure node if there is no method for solving P. If all of the children of a node N, conjoined by the same arc, are success nodes, then the node N is also a success node. Otherwise the node is a failure node. == Search strategies == An and–or tree specifies only the search space for solving a problem. Different search strategies for searching the space are possible. These include searching the tree depth-first, breadth-first, or best-first using some measure of desirability of solutions. The search strategy can be sequential, searching or generating one node at a time, or parallel, searching or generating several nodes in parallel. == Relationship with logic programming == The methods used for generating and–or trees are propositional logic programs (without variables). In the case of logic programs containing variables, the solutions of conjoint sub-problems must be compatible. Subject to this complication, sequential and parallel search strategies for and–or trees provide a computational model for executing logic programs. == Relationship with two-player games == And–or trees can also be used to represent the search spaces for two-person games. The root node of such a tree represents the problem of one of the players winning the game, starting from the initial state of the game. Given a node N, labelled by the problem P of the player winning the game from a particular state of play, there exists a single set of conjoint children nodes, corresponding to all of the opponents responding moves. For each of these children nodes, there exists a set of non-conjoint children nodes, corresponding to all of the player's defending moves. For solving game trees with proof-number search family of algorithms, game trees are to be mapped to and–or trees. MAX-nodes (i.e. maximizing player to move) are represented as OR nodes, MIN-nodes map to AND nodes. The mapping is possible, when the search is done with only a binary goal, which usually is "player to move wins the game".
ByLock
ByLock was a smartphone application that allowed users to communicate via a private, encrypted connection. It was launched in March 2014 on Google Play, Apple App Store The app was downloaded over 600,000 times from its launch in April 2014 until March 2016, when it was permanently shut down. The Turkish National Intelligence Organization (Turkish: Millî İstihbarat Teşkilatı, MİT) stated that the app was downloaded mainly in Turkey and the users were “Fetullahist Terror Organisation (FETÖ) which was formerly known as “Gülen movement” members. == Gülen Movement controversy == In Turkey, possession of the app is deemed evidence of membership in the Gülen Movement, which was allegedly connected to the failed Turkish coup d'état attempt in July 2016. Users of ByLock were deemed terrorists in Turkish courts. According to Deutsche Welle, of the 215,000 former ByLock users, an estimated 23,000 have been detained by Turkish authorities. Some believe that the MİT and other Turkish authorities manipulated the ByLock database in order to arrest suspected members of the Gülen Movement. Tuncay Beşikçi, a computer forensic expert in Turkey, emphasized that "the demands to investigate and analyze ByLock data from independent institutions are refused by the Turkish courts. But it is not normal". Tuncay Beşikçi believes that this application is precisely one of the channels for Gülen molecules to communicate and can also monitor the activities of other members of the organization. He also stated that the developers behind the Mor Beyin app, deliberately set a plan in motion that would put thousands of innocent people in prison as a cover for the Gülen movement. In December 2017, Turkish authorities revealed that almost half the people who had been prosecuted for having ByLock on their smartphones would have their legal cases reviewed, as they could have been redirected to the app without their knowledge. Following the failed coup attempt on 15 July 2016, the use of the ByLock messaging application by members of the Gülen Movement was the sole evidence in investigations and prosecutions to justify arrests and convictions for "membership in an armed terrorist organization." However, these decisions have been considered human rights violations by the European Court of Human Rights (ECHR), the United Nations Human Rights Committee, and the UN Working Group on Arbitrary Detention. Some of the relevant decisions include the following: === Decisions of the European Court of Human Rights === On 20 July 2021, in the case of Tekin Akgün v. Turkey, the European Court of Human Rights (ECHR) ruled that the use of the ByLock messaging application, unless supported by other evidence, does not create a reasonable suspicion of a crime. Based on this reasoning, the court found that the detention order violated Article 5 of the European Convention on Human Rights, which protects the right to liberty and security. In the Yüksel Yalçınkaya v. Turkey decision on 26 September 2023, the European Court of Human Rights (ECHR) examined an appeal against a conviction based on the use of ByLock. The Court ruled that the failure to provide an opportunity to challenge the authenticity of the ByLock data violated the right to a fair trial (Article 6 of the ECHR). The Court also stated that the mere use of ByLock could not be considered sufficient evidence for membership in an armed terrorist organization. It further noted that local courts had established an automatic presumption of guilt based solely on ByLock use, creating a broad and unpredictable interpretation of the law, making it nearly impossible for the accused to exonerate themselves. Therefore, the Court concluded that the conviction based on the use of ByLock violated the principle of no punishment without law (Article 7 of the ECHR). On 22 July 2025, in the Demirhan and 238 Others case, the European Court of Human Rights (ECHR) consolidated the applications of 239 individuals who had been convicted of "membership in an armed terrorist organization" based on their use of ByLock, as determined by 239 separate courts in Turkey. The Court ruled that the convictions violated the right to a fair trial under Article 6 and the principle of no punishment without law under Article 7 of the European Convention on Human Rights (ECHR). The ruling stated that the Turkish courts' "categorical approach" to the use of ByLock lacked legal foundation. In this context, it was emphasized that anyone who had used ByLock could not be convicted of membership in an armed terrorist organization based solely on this reasoning. The ruling also stated that, due to the large number of similar applications, the issue was "systemic in nature" and it called for a national solution to be developed by Turkey. While the Court did not order compensation for the 239 applicants, it emphasized that reopening the trial to ensure the enforcement of the violation ruling was the most appropriate remedy. This ruling, which confirms the violation finding in the Yüksel Yalçınkaya case of 26 September 2023, is considered a continuation of the ECHR's case law concerning trials based on ByLock evidence. === Decisions of the United Nations Human Rights Committee and Working Group === In the İsmet Özçelik and Turgay Karaman v. Turkey decision, dated 28 May 2019 (Application No. 2980/2017), the UN Human Rights Committee ruled that the use of ByLock and allegations of depositing money into Bank Asya could not justify the applicants' arrests. In the Mestan Yayman v. Turkey decision (Opinion No. 42/2018 – 21 August 2018) by the UN Human Rights Council Working Group on Arbitrary Detention, it was stated that using a public messaging application like ByLock cannot be considered criminal evidence, and that the use of such an application falls under the scope of freedom of thought and expression. The dozens of decisions later issued by the UN Human Rights Council Working Group are of the same nature.
Learning automaton
A learning automaton is one type of machine learning algorithm studied since 1970s. Learning automata select their current action based on past experiences from the environment. It will fall into the range of reinforcement learning if the environment is stochastic and a Markov decision process (MDP) is used. == History == Research in learning automata can be traced back to the work of Michael Lvovitch Tsetlin in the early 1960s in the Soviet Union. Together with some colleagues, he published a collection of papers on how to use matrices to describe automata functions. Additionally, Tsetlin worked on reasonable and collective automata behaviour, and on automata games. Learning automata were also investigated by researches in the United States in the 1960s. However, the term learning automaton was not used until Narendra and Thathachar introduced it in a survey paper in 1974. == Definition == A learning automaton is an adaptive decision-making unit situated in a random environment that learns the optimal action through repeated interactions with its environment. The actions are chosen according to a specific probability distribution which is updated based on the environment response the automaton obtains by performing a particular action. With respect to the field of reinforcement learning, learning automata are characterized as policy iterators. In contrast to other reinforcement learners, policy iterators directly manipulate the policy π. Another example for policy iterators are evolutionary algorithms. Formally, Narendra and Thathachar define a stochastic automaton to consist of: a set X of possible inputs, a set Φ = { Φ1, ..., Φs } of possible internal states, a set α = { α1, ..., αr } of possible outputs, or actions, with r ≤ s, an initial state probability vector p(0) = ≪ p1(0), ..., ps(0) ≫, a computable function A which after each time step t generates p(t+1) from p(t), the current input, and the current state, and a function G: Φ → α which generates the output at each time step. In their paper, they investigate only stochastic automata with r = s and G being bijective, allowing them to confuse actions and states. The states of such an automaton correspond to the states of a "discrete-state discrete-parameter Markov process". At each time step t=0,1,2,3,..., the automaton reads an input from its environment, updates p(t) to p(t+1) by A, randomly chooses a successor state according to the probabilities p(t+1) and outputs the corresponding action. The automaton's environment, in turn, reads the action and sends the next input to the automaton. Frequently, the input set X = { 0,1 } is used, with 0 and 1 corresponding to a nonpenalty and a penalty response of the environment, respectively; in this case, the automaton should learn to minimize the number of penalty responses, and the feedback loop of automaton and environment is called a "P-model". More generally, a "Q-model" allows an arbitrary finite input set X, and an "S-model" uses the interval [0,1] of real numbers as X. A visualised demo/ Art Work of a single Learning Automaton had been developed by μSystems (microSystems) Research Group at Newcastle University. == Finite action-set learning automata == Finite action-set learning automata (FALA) are a class of learning automata for which the number of possible actions is finite or, in more mathematical terms, for which the size of the action-set is finite.