AI Assistant In Aem

AI Assistant In Aem — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Flok (company)

Flok (formerly Loyalblocks) was an American tech startup based in New York City that provides marketing services such as chatbots/AI, customer loyalty programs, mobile apps and CRM services to local businesses. In January 2017, the company was acquired by Wix.com. Around March 2017, Flok ceased regular communication. At some point in 2019 Flok communicated to its customers that it would shut down in March 2020. == Background == Flok was founded in 2011 by Ido Gaver and Eran Kirshenboim and has offices in Tel Aviv, Israel. In May 2013, Flok secured a $9 million Series A Round from General Catalyst Partners with participation from Founder Collective and existing investor Gemini Israel Ventures. In total, Flok has raised over $18 million in venture capital in three rounds. In May 2014, Flok announced a self-service loyalty platform for SMBs to build their own programs with beacon integration. At that time, approximately 40,000 businesses were using the service. In 2016, Flok released a turnkey chatbot service for local businesses, and was featured in AdWeek for developing the first weed bot chatbot for a California cannabis business. == Services == Flok offered an eponymous customer-facing app, that consumers use to receive rewards and deals from partner businesses, and a Flok business app for merchants to manage the platform.
Read more →
Resource Description Framework

The Resource Description Framework (RDF) is a method to describe and exchange graph data. It was originally designed as a data model for metadata by the World Wide Web Consortium (W3C). It provides a variety of syntax notations and formats, of which the most widely used is Turtle (Terse RDF Triple Language). RDF is a directed graph composed of triple statements. An RDF graph statement is represented by: (1) a node for the subject, (2) an arc from subject to object, representing a predicate, and (3) a node for the object. Each of these parts can be identified by a Internationalized Resource Identifier (IRI). An object can also be a literal value. This simple, flexible data model has a lot of expressive power to represent complex situations, relationships, and other things of interest, while also being appropriately abstract. RDF was adopted as a W3C recommendation in 1999. The RDF 1.0 specification was published in 2004, and the RDF 1.1 specification in 2014. SPARQL is a standard query language for RDF graphs. RDF Schema (RDFS), Web Ontology Language (OWL) and SHACL (Shapes Constraint Language) are ontology languages that are used to describe RDF data. == Overview == The RDF data model is similar to classical conceptual modeling approaches (such as entity–relationship or class diagrams). It is based on the idea of making statements about resources (in particular web resources) in expressions of the form subject–predicate–object, known as triples. The subject denotes the resource; the predicate denotes traits or aspects of the resource, and expresses a relationship between the subject and the object. For example, one way to represent the notion "The sky has the color blue" in RDF is as the triple: a subject denoting "the sky", a predicate denoting "has the color", and an object denoting "blue". Therefore, RDF uses subject instead of object (or entity) in contrast to the typical approach of an entity–attribute–value model in object-oriented design: entity (sky), attribute (color), and value (blue). RDF is an abstract model with several serialization formats (being essentially specialized file formats). In addition the particular encoding for resources or triples can vary from format to format. This mechanism for describing resources is a major component in the W3C's Semantic Web activity: an evolutionary stage of the World Wide Web in which automated software can store, exchange, and use machine-readable information distributed throughout the Web, in turn enabling users to deal with the information with greater efficiency and certainty. RDF's simple data model and ability to model disparate, abstract concepts has also led to its increasing use in knowledge management applications unrelated to Semantic Web activity. A collection of RDF statements intrinsically represents a labeled, directed multigraph. This makes an RDF data model better suited to certain kinds of knowledge representation than other relational or ontological models. As RDFS, OWL and SHACL demonstrate, one can build additional ontology languages upon RDF. == History == The initial RDF design, intended to "build a vendor-neutral and operating system- independent system of metadata", derived from the W3C's Platform for Internet Content Selection (PICS), an early web content labelling system, but the project was also shaped by ideas from Dublin Core, and from the Meta Content Framework (MCF), which had been developed during 1995 to 1997 by Ramanathan V. Guha at Apple and Tim Bray at Netscape. A first public draft of RDF appeared in October 1997, issued by a W3C working group that included representatives from IBM, Microsoft, Netscape, Nokia, Reuters, SoftQuad, and the University of Michigan. In 1999, the W3C published the first recommended RDF specification, the Model and Syntax Specification ("RDF M&S"). This described RDF's data model and an XML serialization. Two persistent misunderstandings about RDF developed at this time: firstly, due to the MCF influence and the RDF "Resource Description" initialism, the idea that RDF was specifically for use in representing metadata; secondly that RDF was an XML format rather than a data model, and only the RDF/XML serialisation being XML-based. RDF saw little take-up in this period, but there was significant work done in Bristol, around ILRT at Bristol University and HP Labs, and in Boston at MIT. RSS 1.0 and FOAF became exemplar applications for RDF in this period. The recommendation of 1999 was replaced in 2004 by a set of six specifications: "The RDF Primer", "RDF Concepts and Abstract", "RDF/XML Syntax Specification (revised)", "RDF Semantics", "RDF Vocabulary Description Language 1.0", and "The RDF Test Cases". This series was superseded in 2014 by the following six "RDF 1.1" documents: "RDF 1.1 Primer", "RDF 1.1 Concepts and Abstract Syntax", "RDF 1.1 XML Syntax", "RDF 1.1 Semantics", "RDF Schema 1.1", and "RDF 1.1 Test Cases". == RDF topics == === Vocabulary === The vocabulary defined by the RDF specification is as follows: ==== Classes ==== ===== rdf ===== rdf:XMLLiteral the class of XML literal values rdf:Property the class of properties rdf:Statement the class of RDF statements rdf:Alt, rdf:Bag, rdf:Seq containers of alternatives, unordered containers, and ordered containers (rdfs:Container is a super-class of the three) rdf:List the class of RDF Lists rdf:nil an instance of rdf:List representing the empty list ===== rdfs ===== rdfs:Resource the class resource, everything rdfs:Literal the class of literal values, e.g. strings and integers rdfs:Class the class of classes rdfs:Datatype the class of RDF datatypes rdfs:Container the class of RDF containers rdfs:ContainerMembershipProperty the class of container membership properties, rdf:_1, rdf:_2, ..., all of which are sub-properties of rdfs:member ==== Properties ==== ===== rdf ===== rdf:type an instance of rdf:Property used to state that a resource is an instance of a class rdf:first the first item in the subject RDF list rdf:rest the rest of the subject RDF list after rdf:first rdf:value idiomatic property used for structured values rdf:subject the subject of the RDF statement rdf:predicate the predicate of the RDF statement rdf:object the object of the RDF statement rdf:Statement, rdf:subject, rdf:predicate, rdf:object are used for reification (see below). ===== rdfs ===== rdfs:subClassOf the subject is a subclass of a class rdfs:subPropertyOf the subject is a subproperty of a property rdfs:domain a domain of the subject property rdfs:range a range of the subject property rdfs:label a human-readable name for the subject rdfs:comment a description of the subject resource rdfs:member a member of the subject resource rdfs:seeAlso further information about the subject resource rdfs:isDefinedBy the definition of the subject resource This vocabulary is used as a foundation for RDF Schema, where it is extended. === Serialization formats === Several common serialization formats are in use, including: Turtle, a compact, human-friendly format. TriG, an extension of Turtle to datasets. N-Triples, a very simple, easy-to-parse, line-based format that is not as compact as Turtle. N-Quads, a superset of N-Triples, for serializing multiple RDF graphs. JSON-LD, a JSON-based serialization. N3 or Notation3, a non-standard serialization that is very similar to Turtle, but has some additional features, such as the ability to define inference rules. RDF/XML, an XML-based syntax that was the first standard format for serializing RDF. RDF/JSON, an alternative syntax for expressing RDF triples using a simple JSON notation. RDF/XML is sometimes misleadingly called simply RDF because it was introduced among the other W3C specifications defining RDF and it was historically the first W3C standard RDF serialization format. However, it is important to distinguish the RDF/XML format from the abstract RDF model itself. Although the RDF/XML format is still in use, other RDF serializations are now preferred by many RDF users, both because they are more human-friendly, and because some RDF graphs are not representable in RDF/XML due to restrictions on the syntax of XML QNames. With a little effort, virtually any arbitrary XML may also be interpreted as RDF using GRDDL (pronounced 'griddle'), Gleaning Resource Descriptions from Dialects of Languages. RDF triples may be stored in a type of database called a triplestore. === Resource identification === The subject of an RDF statement is either a uniform resource identifier (URI) or a blank node, both of which denote resources. Resources indicated by blank nodes are called anonymous resources. They are not directly identifiable from the RDF statement. The predicate is a URI which also indicates a resource, representing a relationship. The object is a URI, blank node or a Unicode string literal. As of RDF 1.1 resources are identified by Internationalized Resource Identifiers (IRIs); IRIs are a generalization of URIs. In Semantic Web applications, and in re
Read more →
Linear belief function

Linear belief functions are an extension of the Dempster–Shafer theory of belief functions to the case when variables of interest are continuous. Examples of such variables include financial asset prices, portfolio performance, and other antecedent and consequent variables. The theory was originally proposed by Arthur P. Dempster in the context of Kalman Filters and later was elaborated, refined, and applied to knowledge representation in artificial intelligence and decision making in finance and accounting by Liping Liu. == Concept == A linear belief function intends to represent our belief regarding the location of the true value as follows: We are certain that the truth is on a so-called certainty hyperplane but we do not know its exact location; along some dimensions of the certainty hyperplane, we believe the true value could be anywhere from –∞ to +∞ and the probability of being at a particular location is described by a normal distribution; along other dimensions, our knowledge is vacuous, i.e., the true value is somewhere from –∞ to +∞ but the associated probability is unknown. A belief function in general is defined by a mass function over a class of focal elements, which may have nonempty intersections. A linear belief function is a special type of belief function in the sense that its focal elements are exclusive, parallel sub-hyperplanes over the certainty hyperplane and its mass function is a normal distribution across the sub-hyperplanes. Based on the above geometrical description, Shafer and Liu propose two mathematical representations of a LBF: a wide-sense inner product and a linear functional in the variable space, and as their duals over a hyperplane in the sample space. Monney proposes still another structure called Gaussian hints. Although these representations are mathematically neat, they tend to be unsuitable for knowledge representation in expert systems. == Knowledge representation == A linear belief function can represent both logical and probabilistic knowledge for three types of variables: deterministic such as an observable or controllable, random whose distribution is normal, and vacuous on which no knowledge bears. Logical knowledge is represented by linear equations, or geometrically, a certainty hyperplane. Probabilistic knowledge is represented by a normal distribution across all parallel focal elements. In general, assume X is a vector of multiple normal variables with mean μ and covariance Σ. Then, the multivariate normal distribution can be equivalently represented as a moment matrix: M ( X ) = ( μ Σ ) . {\displaystyle M(X)=\left({\begin{array}{{20}c}\mu \\\Sigma \end{array}}\right).} If the distribution is non-degenerate, i.e., Σ has a full rank and its inverse exists, the moment matrix can be fully swept: M ( X → ) = ( μ Σ − 1 − Σ − 1 ) {\displaystyle M({\vec {X}})=\left({\begin{array}{{20}c}\mu \Sigma ^{-1}\\-\Sigma ^{-1}\end{array}}\right)} Except for normalization constant, the above equation completely determines the normal density function for X. Therefore, M ( X → ) {\displaystyle M({\vec {X}})} represents the probability distribution of X in the potential form. These two simple matrices allow us to represent three special cases of linear belief functions. First, for an ordinary normal probability distribution M(X) represents it. Second, suppose one makes a direct observation on X and obtains a value μ. In this case, since there is no uncertainty, both variance and covariance vanish, i.e., Σ = 0. Thus, a direct observation can be represented as: M ( X ) = ( μ 0 ) {\displaystyle M(X)=\left({\begin{array}{{20}c}\mu \\0\end{array}}\right)} Third, suppose one is completely ignorant about X. This is a very thorny case in Bayesian statistics since the density function does not exist. By using the fully swept moment matrix, we represent the vacuous linear belief functions as a zero matrix in the swept form follows: M ( X → ) = [ 0 0 ] {\displaystyle M({\vec {X}})=\left[{\begin{array}{{20}c}0\\0\end{array}}\right]} One way to understand the representation is to imagine complete ignorance as the limiting case when the variance of X approaches to ∞, where one can show that Σ−1 = 0 and hence M ( X → ) {\displaystyle M({\vec {X}})} vanishes. However, the above equation is not the same as an improper prior or normal distribution with infinite variance. In fact, it does not correspond to any unique probability distribution. For this reason, a better way is to understand the vacuous linear belief functions as the neutral element for combination (see later). To represent the remaining three special cases, we need the concept of partial sweeping. Unlike a full sweeping, a partial sweeping is a transformation on a subset of variables. Suppose X and Y are two vectors of normal variables with the joint moment matrix: M ( X , Y ) = [ μ 1 Σ 11 Σ 21 μ 2 Σ 12 Σ 22 ] {\displaystyle M(X,Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}\mu _{1}\\\Sigma _{11}\\\Sigma _{21}\end{array}}&{\begin{array}{{20}c}\mu _{2}\\\Sigma _{12}\\\Sigma _{22}\end{array}}\end{array}}\right]} Then M(X, Y) may be partially swept. For example, we can define the partial sweeping on X as follows: M ( X → , Y ) = [ μ 1 ( Σ 11 ) − 1 − ( Σ 11 ) − 1 Σ 21 ( Σ 11 ) − 1 μ 2 − μ 1 ( Σ 11 ) − 1 Σ 12 ( Σ 11 ) − 1 Σ 12 Σ 22 − Σ 21 ( Σ 11 ) − 1 Σ 12 ] {\displaystyle M({\vec {X}},Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}\mu _{1}(\Sigma _{11})^{-1}\\-(\Sigma _{11})^{-1}\\\Sigma _{21}(\Sigma _{11})^{-1}\end{array}}&{\begin{array}{{20}c}\mu _{2}-\mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}\\(\Sigma _{11})^{-1}\Sigma _{12}\\\Sigma _{22}-\Sigma _{21}(\Sigma _{11})^{-1}\Sigma _{12}\end{array}}\end{array}}\right]} If X is one-dimensional, a partial sweeping replaces the variance of X by its negative inverse and multiplies the inverse with other elements. If X is multidimensional, the operation involves the inverse of the covariance matrix of X and other multiplications. A swept matrix obtained from a partial sweeping on a subset of variables can be equivalently obtained by a sequence of partial sweepings on each individual variable in the subset and the order of the sequence does not matter. Similarly, a fully swept matrix is the result of partial sweepings on all variables. We can make two observations. First, after the partial sweeping on X, the mean vector and covariance matrix of X are respectively μ 1 ( Σ 11 ) − 1 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}} and − ( Σ 11 ) − 1 {\displaystyle -(\Sigma _{11})^{-1}} , which are the same as that of a full sweeping of the marginal moment matrix of X. Thus, the elements corresponding to X in the above partial sweeping equation represent the marginal distribution of X in potential form. Second, according to statistics, μ 2 − μ 1 ( Σ 11 ) − 1 Σ 12 {\displaystyle \mu _{2}-\mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}} is the conditional mean of Y given X = 0; Σ 22 − Σ 21 ( Σ 11 ) − 1 Σ 12 {\displaystyle \Sigma _{22}-\Sigma _{21}(\Sigma _{11})^{-1}\Sigma _{12}} is the conditional covariance matrix of Y given X = 0; and ( Σ 11 ) − 1 Σ 12 {\displaystyle (\Sigma _{11})^{-1}\Sigma _{12}} is the slope of the regression model of Y on X. Therefore, the elements corresponding to Y indices and the intersection of X and Y in M ( X → , Y ) {\displaystyle M({\vec {X}},Y)} represents the conditional distribution of Y given X = 0. These semantics render the partial sweeping operation a useful method for manipulating multivariate normal distributions. They also form the basis of the moment matrix representations for the three remaining important cases of linear belief functions, including proper belief functions, linear equations, and linear regression models. === Proper linear belief functions === For variables X and Y, assume there exists a piece of evidence justifying a normal distribution for variables Y while bearing no opinions for variables X. Also, assume that X and Y are not perfectly linearly related, i.e., their correlation is less than 1. This case involves a mix of an ordinary normal distribution for Y and a vacuous belief function for X. Thus, we represent it using a partially swept matrix as follows: M ( X → , Y ) = [ 0 0 0 μ 2 0 Σ 22 ] {\displaystyle M({\vec {X}},Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}0\\0\\0\end{array}}&{\begin{array}{{20}c}\mu _{2}\\0\\\Sigma _{22}\\\end{array}}\end{array}}\right]} This is how we could understand the representation. Since we are ignorant on X, we use its swept form and set μ 1 ( Σ 11 ) − 1 = 0 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}=0} and − ( Σ 11 ) − 1 = 0 {\displaystyle -(\Sigma _{11})^{-1}=0} . Since the correlation between X and Y is less than 1, the regression coefficient of X on Y approaches to 0 when the variance of X approaches to ∞. Therefore, ( Σ 11 ) − 1 Σ 12 = 0 {\displaystyle (\Sigma _{11})^{-1}\Sigma _{12}=0} . Similarly, one can prove that μ 1 ( Σ 11 ) − 1 Σ 12 = 0 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}=0} and Σ 21 ( Σ 11 ) −
Read more →
Moral Machine

Moral Machine is an online platform, developed by Iyad Rahwan's Scalable Cooperation group at the Massachusetts Institute of Technology, that generates moral dilemmas and collects information on the decisions that people make between two destructive outcomes. The platform is the idea of Iyad Rahwan and social psychologists Azim Shariff and Jean-François Bonnefon, who conceived of the idea ahead of the publication of their article about the ethics of self-driving cars. The key contributors to building the platform were MIT Media Lab graduate students Edmond Awad and Sohan Dsouza. The presented scenarios are often variations of the trolley problem, and the information collected would be used for further research regarding the decisions that machine intelligence must make in the future. For example, as artificial intelligence plays an increasingly significant role in autonomous driving technology, research projects like Moral Machine help to find solutions for challenging life-and-death decisions that will face self-driving vehicles. Moral Machine was active from January 2016 to July 2020. The Moral Machine continues to be available on their website for people to experience. == The experiment == The Moral Machine was an ambitious project; it was the first attempt at using such an experimental design to test a large number of humans in over 200 countries worldwide. The study was approved by the Institute Review Board (IRB) at Massachusetts Institute of Technology (MIT). The setup of the experiment asks the viewer to make a decision on a single scenario in which a self-driving car is about to hit pedestrians. The user can decide to have the car either swerve to avoid hitting the pedestrians or keep going straight to preserve the lives it is transporting. Participants can complete as many scenarios as they want to, however the scenarios themselves are generated in groups of thirteen. Within this thirteen, a single scenario is entirely random while the other twelve are generated from a space in a database of 26 million different possibilities. They are chosen with two dilemmas focused on each of six dimensions of moral preferences: character gender, character age, character physical fitness, character social status, character species, and character number. The experiment setup remains the same throughout multiple scenarios but each scenario tests a different set of factors. Most notably, the characters involved in the scenario are different in each one. Characters may include ones such as: Stroller, girl, boy, pregnant, Male Doctor, Female Doctor, Female Athlete, Executive Female, Male Athlete, Executive Male, Large Woman, Large Man, homeless, old man, old woman, dog, criminal, and a cat. Through these different characters researchers were able to understand how a wide variety of people will judge scenarios based on those involved. == Analysis == The Moral Machine collected 40 million moral decisions from 4 million participants in 233 countries, analysis of which revealed trends within individual countries and humanity as a whole. It tested for nine factors: preference for sparing humans versus pets, passengers versus pedestrians, men versus women, young versus elderly, fit versus overweight, higher versus lower social status, jaywalkers versus law abiders, larger versus smaller groups, and inaction (i.e. staying on course) versus swerving. Globally, participants favored human lives over lives of animals like dogs and cats. They preferred to spare more lives if possible, and younger lives as opposed to older. Babies were most often spared with cats being the least spared. In terms of gender variations, people tended to spare men over women for doctors and the elderly. All countries generally shared the preference to spare pedestrians over passengers and law-abiders over criminals. Participants from less wealthy countries showed a higher tendency of sparing pedestrians who crossed illegally compared to those from more wealthy and developed countries. This is most likely due to their experience living in a society where individuals are more likely to deviate from rules due to less stringent enforcement of laws. Countries of higher economic inequality overwhelmingly prefer to save wealthier individuals over poorer ones. === Cultural differences === Researchers subdivided 130 countries with similar results into three ‘cultural clusters’. North America and European countries with significant Christian populations had a higher preference for inaction on the part of the driver and thus had less of a preference for sparing pedestrians as compared to other clusters. East Asian and Islamic countries, together constituting the second cluster, did not have as much preference to spare younger humans compared to the other two clusters and had a higher preference for sparing law-abiding humans. Latin America and Francophone countries had a higher preference for sparing women, the young, the fit, and those of higher status, but a lower preference for sparing humans over pets or other animals. Individualistic cultures tended to spare larger groups, and collectivist cultures had a stronger preference for sparing the lives of older people. For instance, China ranked far below the world average for preference to spare the younger over elderly, while the average respondent from the US exhibited a much higher tendency to save younger lives and larger groups. == Applications of the data == The findings from the moral machine can help decision makers when designing self-driving automotive systems. Designers must make sure that these vehicles are able to solve problems on the road that aligns with the moral values of humans around it. This is a challenge because of the complex nature of humans who may all make different decisions based on their personal values. However, by collecting a large amount of decisions from humans all over the world, researchers can begin to understand patterns in the context of a particular culture, community, and people. == Other features == The Moral Machine was deployed in June 2016. In October 2016, a feature was added that offered users the option to fill a survey about their demographics, political views, and religious beliefs. Between November 2016 and March 2017, the website was progressively translated into nine languages in addition to English (Arabic, Chinese, French, German, Japanese, Korean, Portuguese, Russian, and Spanish). Overall, the Moral Machine offers four different modes, with the focus being on the data-gathering feature of the website, called the Judge mode. This means that the Moral Machine, in addition to providing their own scenarios for users to judge, also invites users to create their own scenarios to be submitted and approved so that other people may also judge those scenarios. Data is also open sourced for anyone to explore via an interactive map that is featured on the Moral Machine website. == In the literature == Studies and research on the Moral Machine have taken a wide variety of approaches. However, theological examinations of the topic are still scarce where two bodies of work that examine such perspective currently exist in this regard: One is Buddhist while the other is Christian.
Read more →
Label noise

Label noise refers to errors or inaccuracies in the class labels of data instances. This is a widespread issue in machine learning datasets, arising from human annotator mistakes, unclear labeling instructions, automated labeling methods, or adversarial attacks in supervised learning. Label noise can be roughly divided into random noise, where labels are flipped independently of input features, and systematic noise, where mislabeling is dependent on certain patterns or biases in the data. Label noise can be damaging to model performance, especially for complex models that may overfit to noisy labels rather than generalizable patterns. Many approaches have been proposed to deal with the effects of label noise, including robust loss functions, noise-tolerant algorithms, data cleaning methods, and semi-supervised learning approaches. To reduce the impact of wrong labels during training, techniques like label smoothing, sample reweighting and using trusted validation sets are used. The role of noise-robust training paradigms and curriculum learning strategies to improve resilience against mislabeled data is also explored in recent research.
Read more →
Script theory

Script theory is a psychological theory which posits that human behaviour largely falls into patterns called scripts because they function the way a written script does, by providing a program for action. Silvan Tomkins created script theory as a further development of his affect theory, which regards human beings' emotional responses to stimuli as falling into categories called affects: he noticed that the purely biological response of affect may be followed by awareness and by what we cognitively do in terms of acting on that affect, so that more was needed to produce a complete explanation of what he called human being theory. These scripts fall under the larger cognitive concept called schemas, which are organized chunks of information. A schema is a script that has the potential to lack the specificity of the sequence of events. A schema becomes a script is when there is an ordering to it that requires action, such as the process of starting a car (get in, put on the seatbelt, turn the car on, release the emergency brake, etc.). In script theory, the basic unit of analysis is called a scene, defined as a sequence of events linked by the affects triggered during the experience of those events. Tomkins recognized that affective experiences fall into patterns that we may group together according to criteria, such as the types of persons and places involved and the degree of intensity of the effect experienced—the patterns of which constitute scripts that inform behavior in an effort to maximize positive affect and to minimize negative affect. == In artificial intelligence == Roger Schank, Robert P. Abelson and their research group extended Tomkins' scripts and used them in early artificial intelligence work as a method of representing procedural knowledge. In their work, scripts are very much like frames, except the values that fill the slots must be ordered. A script is a structured representation describing a stereotyped sequence of events in a particular context. Scripts are used in natural-language understanding systems to organize a knowledge base in terms of the situations that the system should understand. The classic example of a script involves the typical sequence of events that occur when a person drinks in a restaurant: finding a seat, reading the menu, ordering drinks from the waitstaff, etc. In the script form, these would be decomposed into conceptual transitions, such as MTRANS and PTRANS, which refer to mental transitions [of information] and physical transitions [of things]. Schank, Abelson and their colleagues tackled some of the most difficult problems in artificial intelligence (i.e., story understanding), but ultimately their line of work ended without tangible success. This type of work received little attention after the 1980s, but became very influential in later knowledge representation techniques, such as case-based reasoning. Scripts can be inflexible. To deal with inflexibility, smaller modules called memory organization packets (MOP) can be combined in a way that is appropriate for the situation.
Read more →
Generative AI Copyright Disclosure Act

The Generative AI Copyright Disclosure Act is a piece of legislation introduced by California Representative Adam Schiff in the United States Congress on April 9, 2024. It concerns the transparency of companies regarding their use of copyrighted work to train their generative artificial intelligence (AI) models. The legislation requires the submission of a notice regarding the identity and the uniform resource locator (URL) address of the copyrighted works used in the training data to the Register of Copyrights at least 30 days before the public release of the new or updated version of the AI model; it does not ban the use of copyrighted works for AI training. The bill's requirements would apply retroactively to prior AI models. Violation penalties would start at US$5,000. The legislation does not have a maximum penalty assessment that can be charged. The bill by Schiff was introduced a few days after The New York Times published an article regarding the business activities of major tech firms, including Google and Meta, in the training of their generative AI platforms on April 6, 2024. The legislation is supported by the Professional Photographers of America (PPA), SAG-AFTRA, the Writers Guild of America, the International Alliance of Theatrical Stage Employees (IATSE), the Recording Industry Association of America (RIAA), and others.
Read more →
Jess (programming language)

Jess is a rule engine for the Java computing platform, written in the Java programming language. It was developed by Ernest Friedman-Hill of Sandia National Laboratories. It is a superset of the CLIPS language. It was first written in late 1995. The language provides rule-based programming for the automation of an expert system, and is often termed as an expert system shell. In recent years, intelligent agent systems have also developed, which depend on a similar ability. Rather than a procedural paradigm, where one program has a loop that is activated only one time, the declarative paradigm used by Jess applies a set of rules to a set of facts continuously by a process named pattern matching. Rules can modify the set of facts, or can execute any Java code. It uses the Rete algorithm to execute rules. == License == The licensing for Jess is freeware for education and government use, and is proprietary software, needing a license, for commercial use. In contrast, CLIPS, which is the basis and starting code for Jess, is free and open-source software. == Code examples == Code examples: Sample code:
Read more →
Film-out

Film-out is the process in the computer graphics, video production and filmmaking disciplines of transferring images or animation from videotape or digital files to a traditional film print. Film-out is a broad term that encompasses the conversion of frame rates, color correction, as well as the actual printing, also called scannior recording. The film-out process is different depending on the regional standard of the master videotape in question – NTSC, PAL, or SECAM – or likewise on the several emerging region-independent formats of high definition video (HD video); thus each type is covered separately, taking into account regional film-out industries, methods and technical considerations. == Live action video == Many modern documentaries and low-budget films are shot on videotape or other digital video media, instead of film stock, and completed as digital video. Video production means substantially lower costs than 16 mm or 35 mm film production on all levels. Until recently, the relatively low cost of video ended when the issue of a theatrical presentation was raised, which required a print for film projection. With the growing presence of digital projection, this is becoming less of a factor. === Standard definition (SD) video === Film-out of standard-definition video – or any source that has an incompatible frame rate – is the up-conversion of video media to film for theatrical viewing. The video-to-film conversion process consists of two major steps: first, the conversion of video into digital film frames which are then stored on a computer or on HD videotape; and secondly, the printing of these digital film frames onto actual film. To understand these two steps, it is important to understand how video and film differ. Film (sound film, at least) has remained unchanged for almost a century and creates the illusion of moving images through the rapid projection of still images, frames, upon a screen, typically 24 per second. Traditional interlaced SD video has no real frame rate, (though the term frame is applied to video, it has a different meaning). Instead, video consists of a very fast succession of horizontal lines that continually cascade down the television screen – streaming top to bottom, before jumping back to the top and then streaming down to the bottom again, repeatedly, almost 60 alternating screen-fulls every second for NTSC, or exactly 50 such screen-fulls per second for PAL and SECAM. Since visual movement in video is infused in this continuous cascade of scan lines, there is no discrete image or real frame that can be identified at any one time. Therefore, when transferring video to film, it is necessary to invent individual film frames, 24 for every second of elapsed time. The bulk of the work done by a film-out company is this first step, creating film frames out of the stream of interlaced video. Each company employs its own (often proprietary) technology for turning interlaced video into high-resolution digital video files of 24 discrete images every second, called 24 progressive video or 24p. The technology must filter out all the visually unappealing artifacting that results from the inherent mismatch between video and film movement. Moreover, the conversion process usually requires human intervention at every edit point of a video program, so that each type of scene can be calibrated for maximum visual quality. The use of archival footage in video especially calls for extra attention. Step two, the scanning to film, is the rote part of the process. This is the mechanical step where lasers print each of the newly created frames of the 24p video, stored on computer files or HD videotape, onto rolls of film. Most companies that do film-out, do all the stages of the process themselves for a lump sum. The job includes converting interlaced video into 24p and often a color correction session – (calibrating the image for theatrical projection), before scanning to physical film, (possibly followed by color correction of the film print made from the digital intermediary) – is offered. At the very least, film-out can be understood as the process of converting interlaced video to 24p and then scanning it to film. ==== NTSC video ==== NTSC is the most challenging of the formats when it comes to standards conversion and, specifically, converting to film prints. NTSC runs at the approximate rate of 29.97 video frames (consisting of two interlaced screen-fulls of scan lines, called fields, per frame) per second. In this way, NTSC resolves actual live action movement at almost – but not quite – 60 alternating half-resolution images every second. Because of this 29.97 rate, no direct correlation to film frames at 24 frames per second can be achieved. NTSC is hardest to reconcile with film, thus motivating its own unique processes. ==== PAL and SECAM video ==== PAL and SECAM run at 25 interlaced video frames per second, which can be slowed down or frame-dropped, then deinterlaced, to correlate frame for frame with film running at 24 actual frames per second. PAL and SECAM are less complex and demanding than NTSC for film-out. PAL and SECAM conversions do agitate, though, with the unpleasant choice between slowing down video (and audio pitch, noticeably) by four percent, from 25 to 24 frames per second, in order to maintain a 1:1 frame match, slightly changing the rhythm and feel of the program; or maintaining original speed by periodically dropping frames, thereby creating jerkiness and possible loss of vital detail in fast-moving action or precise edits. === High definition (HD) digital video === High definition digital video can be shot at a variety of frame rates, including 29.97 interlaced (like NTSC) or progressive; or 25 interlaced (like PAL) or progressive; or even 24-progressive (just like film). HD, if shot in 24-progressive, scans nearly perfectly to film without the need for a frame or field conversion process. Other issues remain though, based on the different resolutions, color spaces, and compression schemes that exist in the high-definition video world. == Computer graphics and animation == Artists working with CGI-Computer-generated imagery animation computers create pictures frame by frame. Once the finished product is done, the frames are outputted, normally in a DPX file. These picture data files can then be put on to film using a film recorder for film out. SGI computers started the high-end CGI-Computer-generated imagery animation systems, but with faster computers and the growth of Linux-based systems, many others are on the market now. Movies fully rendered and animated in CGI such as Toy Story, and Antz utilize the film-out method to produce 35mm copies for archival and release prints. Most CGI work is done in 2K Display resolution files (about the size of QXGA) and then output to the Film-out device for creation of 35 mm elements. With 4K Display resolution digital intermediates on the rise, newer types of film-out recorders are being developed to accept 4k resolution files. A 2K movie requires a Storage Area Network storage several terabytes in size to be properly stored and played out. Computer graphics files are handled the same way but in single frames and may use DPX, TIFF or other file formats. == Digital intermediates == Film-out-recording is the last step of digital intermediate workflow. DPX files that were scanned on a motion picture film scanner are stored on a storage area network (often abbreviated as SAN). The scanned DPX footage is edited and composited-FX on workstations, then mastered back on film. Film restoration is also done this way. A "film intermediate" is an analog variation of a digital intermediate, where a project shot on digital video is printed onto film stock and transferred back to digital video to emulate film. The term was coined after it was used on the Oscar-winning 2012 short film "Curfew". The process was also used on the films Dune (2021) and The Batman (2022). == Images for graphic design and print industries == The days of newspapers and magazines shooting 35mm film are almost gone. Digital cameras can now shoot all the images needed, storing them as files (e.g. JPEG, DPX or another format) that are readily edited prior to use. Once the final copy is approved, it can be filmed out for publishing. Digital stills are not the only way to get pictures used in the graphic design and print industries. Film scanners and computer graphics programs are also common sources for graphic design and print industries. == Types of devices == The following devices are used in film-out processes: CRT recorder. Camera and a special TV display Kinescope – early type Electronic Video Recording or EVR – early type EBR Electron Beam Film Recorder 16 mm by 3M Laser film recorder, like Kodak's high-end Lightning II recorder and Arri's Arrilaser. DLP Film recorder, like Cinevation's real-time Cinevator. == History == Lately it has become possible to transfer video images, inclu
Read more →
Linear belief function

Linear belief functions are an extension of the Dempster–Shafer theory of belief functions to the case when variables of interest are continuous. Examples of such variables include financial asset prices, portfolio performance, and other antecedent and consequent variables. The theory was originally proposed by Arthur P. Dempster in the context of Kalman Filters and later was elaborated, refined, and applied to knowledge representation in artificial intelligence and decision making in finance and accounting by Liping Liu. == Concept == A linear belief function intends to represent our belief regarding the location of the true value as follows: We are certain that the truth is on a so-called certainty hyperplane but we do not know its exact location; along some dimensions of the certainty hyperplane, we believe the true value could be anywhere from –∞ to +∞ and the probability of being at a particular location is described by a normal distribution; along other dimensions, our knowledge is vacuous, i.e., the true value is somewhere from –∞ to +∞ but the associated probability is unknown. A belief function in general is defined by a mass function over a class of focal elements, which may have nonempty intersections. A linear belief function is a special type of belief function in the sense that its focal elements are exclusive, parallel sub-hyperplanes over the certainty hyperplane and its mass function is a normal distribution across the sub-hyperplanes. Based on the above geometrical description, Shafer and Liu propose two mathematical representations of a LBF: a wide-sense inner product and a linear functional in the variable space, and as their duals over a hyperplane in the sample space. Monney proposes still another structure called Gaussian hints. Although these representations are mathematically neat, they tend to be unsuitable for knowledge representation in expert systems. == Knowledge representation == A linear belief function can represent both logical and probabilistic knowledge for three types of variables: deterministic such as an observable or controllable, random whose distribution is normal, and vacuous on which no knowledge bears. Logical knowledge is represented by linear equations, or geometrically, a certainty hyperplane. Probabilistic knowledge is represented by a normal distribution across all parallel focal elements. In general, assume X is a vector of multiple normal variables with mean μ and covariance Σ. Then, the multivariate normal distribution can be equivalently represented as a moment matrix: M ( X ) = ( μ Σ ) . {\displaystyle M(X)=\left({\begin{array}{{20}c}\mu \\\Sigma \end{array}}\right).} If the distribution is non-degenerate, i.e., Σ has a full rank and its inverse exists, the moment matrix can be fully swept: M ( X → ) = ( μ Σ − 1 − Σ − 1 ) {\displaystyle M({\vec {X}})=\left({\begin{array}{{20}c}\mu \Sigma ^{-1}\\-\Sigma ^{-1}\end{array}}\right)} Except for normalization constant, the above equation completely determines the normal density function for X. Therefore, M ( X → ) {\displaystyle M({\vec {X}})} represents the probability distribution of X in the potential form. These two simple matrices allow us to represent three special cases of linear belief functions. First, for an ordinary normal probability distribution M(X) represents it. Second, suppose one makes a direct observation on X and obtains a value μ. In this case, since there is no uncertainty, both variance and covariance vanish, i.e., Σ = 0. Thus, a direct observation can be represented as: M ( X ) = ( μ 0 ) {\displaystyle M(X)=\left({\begin{array}{{20}c}\mu \\0\end{array}}\right)} Third, suppose one is completely ignorant about X. This is a very thorny case in Bayesian statistics since the density function does not exist. By using the fully swept moment matrix, we represent the vacuous linear belief functions as a zero matrix in the swept form follows: M ( X → ) = [ 0 0 ] {\displaystyle M({\vec {X}})=\left[{\begin{array}{{20}c}0\\0\end{array}}\right]} One way to understand the representation is to imagine complete ignorance as the limiting case when the variance of X approaches to ∞, where one can show that Σ−1 = 0 and hence M ( X → ) {\displaystyle M({\vec {X}})} vanishes. However, the above equation is not the same as an improper prior or normal distribution with infinite variance. In fact, it does not correspond to any unique probability distribution. For this reason, a better way is to understand the vacuous linear belief functions as the neutral element for combination (see later). To represent the remaining three special cases, we need the concept of partial sweeping. Unlike a full sweeping, a partial sweeping is a transformation on a subset of variables. Suppose X and Y are two vectors of normal variables with the joint moment matrix: M ( X , Y ) = [ μ 1 Σ 11 Σ 21 μ 2 Σ 12 Σ 22 ] {\displaystyle M(X,Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}\mu _{1}\\\Sigma _{11}\\\Sigma _{21}\end{array}}&{\begin{array}{{20}c}\mu _{2}\\\Sigma _{12}\\\Sigma _{22}\end{array}}\end{array}}\right]} Then M(X, Y) may be partially swept. For example, we can define the partial sweeping on X as follows: M ( X → , Y ) = [ μ 1 ( Σ 11 ) − 1 − ( Σ 11 ) − 1 Σ 21 ( Σ 11 ) − 1 μ 2 − μ 1 ( Σ 11 ) − 1 Σ 12 ( Σ 11 ) − 1 Σ 12 Σ 22 − Σ 21 ( Σ 11 ) − 1 Σ 12 ] {\displaystyle M({\vec {X}},Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}\mu _{1}(\Sigma _{11})^{-1}\\-(\Sigma _{11})^{-1}\\\Sigma _{21}(\Sigma _{11})^{-1}\end{array}}&{\begin{array}{{20}c}\mu _{2}-\mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}\\(\Sigma _{11})^{-1}\Sigma _{12}\\\Sigma _{22}-\Sigma _{21}(\Sigma _{11})^{-1}\Sigma _{12}\end{array}}\end{array}}\right]} If X is one-dimensional, a partial sweeping replaces the variance of X by its negative inverse and multiplies the inverse with other elements. If X is multidimensional, the operation involves the inverse of the covariance matrix of X and other multiplications. A swept matrix obtained from a partial sweeping on a subset of variables can be equivalently obtained by a sequence of partial sweepings on each individual variable in the subset and the order of the sequence does not matter. Similarly, a fully swept matrix is the result of partial sweepings on all variables. We can make two observations. First, after the partial sweeping on X, the mean vector and covariance matrix of X are respectively μ 1 ( Σ 11 ) − 1 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}} and − ( Σ 11 ) − 1 {\displaystyle -(\Sigma _{11})^{-1}} , which are the same as that of a full sweeping of the marginal moment matrix of X. Thus, the elements corresponding to X in the above partial sweeping equation represent the marginal distribution of X in potential form. Second, according to statistics, μ 2 − μ 1 ( Σ 11 ) − 1 Σ 12 {\displaystyle \mu _{2}-\mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}} is the conditional mean of Y given X = 0; Σ 22 − Σ 21 ( Σ 11 ) − 1 Σ 12 {\displaystyle \Sigma _{22}-\Sigma _{21}(\Sigma _{11})^{-1}\Sigma _{12}} is the conditional covariance matrix of Y given X = 0; and ( Σ 11 ) − 1 Σ 12 {\displaystyle (\Sigma _{11})^{-1}\Sigma _{12}} is the slope of the regression model of Y on X. Therefore, the elements corresponding to Y indices and the intersection of X and Y in M ( X → , Y ) {\displaystyle M({\vec {X}},Y)} represents the conditional distribution of Y given X = 0. These semantics render the partial sweeping operation a useful method for manipulating multivariate normal distributions. They also form the basis of the moment matrix representations for the three remaining important cases of linear belief functions, including proper belief functions, linear equations, and linear regression models. === Proper linear belief functions === For variables X and Y, assume there exists a piece of evidence justifying a normal distribution for variables Y while bearing no opinions for variables X. Also, assume that X and Y are not perfectly linearly related, i.e., their correlation is less than 1. This case involves a mix of an ordinary normal distribution for Y and a vacuous belief function for X. Thus, we represent it using a partially swept matrix as follows: M ( X → , Y ) = [ 0 0 0 μ 2 0 Σ 22 ] {\displaystyle M({\vec {X}},Y)=\left[{\begin{array}{{20}c}{\begin{array}{{20}c}0\\0\\0\end{array}}&{\begin{array}{{20}c}\mu _{2}\\0\\\Sigma _{22}\\\end{array}}\end{array}}\right]} This is how we could understand the representation. Since we are ignorant on X, we use its swept form and set μ 1 ( Σ 11 ) − 1 = 0 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}=0} and − ( Σ 11 ) − 1 = 0 {\displaystyle -(\Sigma _{11})^{-1}=0} . Since the correlation between X and Y is less than 1, the regression coefficient of X on Y approaches to 0 when the variance of X approaches to ∞. Therefore, ( Σ 11 ) − 1 Σ 12 = 0 {\displaystyle (\Sigma _{11})^{-1}\Sigma _{12}=0} . Similarly, one can prove that μ 1 ( Σ 11 ) − 1 Σ 12 = 0 {\displaystyle \mu _{1}(\Sigma _{11})^{-1}\Sigma _{12}=0} and Σ 21 ( Σ 11 ) −
Read more →
LightGBM

LightGBM, short for Light Gradient-Boosting Machine, is a free and open-source distributed gradient-boosting framework for machine learning, originally developed by Microsoft. It is based on decision tree algorithms and used for ranking, classification and other machine learning tasks. The development focus is on performance and scalability. == Overview == The LightGBM framework supports different algorithms including GBT, GBDT, GBRT, GBM, MART and RF. LightGBM has many of XGBoost's advantages, including sparse optimization, parallel training, multiple loss functions, regularization, bagging, and early stopping. A major difference between the two lies in the construction of trees. LightGBM does not grow a tree level-wise — row by row — as most other implementations do. Instead it grows trees leaf-wise. It will choose the leaf with max delta loss to grow. Besides, LightGBM does not use the widely used sorted-based decision tree learning algorithm, which searches the best split point on sorted feature values, as XGBoost or other implementations do. Instead, LightGBM implements a highly optimized histogram-based decision tree learning algorithm, which yields great advantages on both efficiency and memory consumption. The LightGBM algorithm utilizes two novel techniques called Gradient-Based One-Side Sampling (GOSS) and Exclusive Feature Bundling (EFB) which allow the algorithm to run faster while maintaining a high level of accuracy. LightGBM works on Linux, Windows, and macOS and supports C++, Python, R, and C#. The source code is licensed under MIT License and available on GitHub. == Gradient-based one-side sampling == When using gradient descent, one thinks about the space of possible configurations of the model as a valley, in which the lowest part of the valley is the model which most closely fits the data. In this metaphor, one walks in different directions to learn how much lower the valley becomes. Typically, in gradient descent, one uses the whole set of data to calculate the valley's slopes. However, this commonly used method assumes that every data point is equally informative. By contrast, Gradient-Based One-Side Sampling (GOSS), a method first developed for gradient-boosted decision trees, does not rely on the assumption that all data are equally informative. Instead, it treats data points with smaller gradients (shallower slopes) as less informative by randomly dropping them. This is intended to filter out data which may have been influenced by noise, allowing the model to more accurately model the underlying relationships in the data. == Exclusive feature bundling == Exclusive feature bundling (EFB) is a near-lossless method to reduce the number of effective features. In a sparse feature space many features are nearly exclusive, implying they rarely take nonzero values simultaneously. One-hot encoded features are a perfect example of exclusive features. EFB bundles these features, reducing dimensionality to improve efficiency while maintaining a high level of accuracy. The bundle of exclusive features into a single feature is called an exclusive feature bundle.
Read more →
Knowledge space

In mathematical psychology and education theory, a knowledge space is a combinatorial structure used to formulate mathematical models describing the progression of a human learner. Knowledge spaces were introduced in 1985 by Jean-Paul Doignon and Jean-Claude Falmagne, and remain in extensive use in the education theory. Modern applications include two computerized tutoring systems, ALEKS and the defunct RATH. Formally, a knowledge space assumes that a domain of knowledge is a collection of concepts or skills, each of which must be eventually mastered. Not all concepts are interchangeable; some require other concepts as prerequisites. Conversely, competency at one skill may ease the acquisition of another through similarity. A knowledge space marks out which collections of skills are feasible: they can be learned without mastering any other skills. Under reasonable assumptions, the collection of feasible competencies forms the mathematical structure known as an antimatroid. Researchers and educators usually explore the structure of a discipline's knowledge space as a latent class model. == Motivation == Knowledge Space Theory attempts to address shortcomings of standardized testing when used in educational psychometry. Common tests, such as the SAT and ACT, compress a student's knowledge into a very small range of ordinal ranks, in the process effacing the conceptual dependencies between questions. Consequently, the tests cannot distinguish between true understanding and guesses, nor can they identify a student's particular weaknesses, only the general proportion of skills mastered. The goal of knowledge space theory is to provide a language by which exams can communicate What the student can do and What the student is ready to learn. == Model structure == Knowledge Space Theory-based models presume that an educational subject S can be modeled as a finite set Q of concepts, skills, or topics. Each feasible state of knowledge about S is then a subset of Q; the set of all such feasible states is K. The precise term for the information (Q, K) depends on the extent to which K satisfies certain axioms: A knowledge structure assumes that K contains the empty set (a student may know nothing about S) and Q itself (a student may have fully mastered S). A knowledge space is a knowledge structure that is closed under set union: if, for each topic, there is an expert in a class on that topic, then it is possible, with enough time and effort, for each student in the class to become an expert on all those topics simultaneously. A quasi-ordinal knowledge space is a knowledge space that is also closed under set intersection: if student a knows topics A and B; and student c knows topics B and C; then it is possible for another student b to know only topic B. A well-graded knowledge space or learning space is a knowledge space satisfying the following axiom: If S∈K, then there exists x∈S such that S\{x}∈K In educational terms, any feasible body of knowledge can be learned one concept at a time. === Prerequisite partial order === The more contentful axioms associated with quasi-ordinal and well-graded knowledge spaces each imply that the knowledge space forms a well-understood (and heavily studied) mathematical structure: A quasi-ordinal knowledge space can be associated with a distributive lattice under set union and set intersection. The name "quasi-ordinal" arises from Birkhoff's representation theorem, which explains that distributive lattices uniquely correspond to partial orders. A well-graded knowledge space is an antimatroid, a type of mathematical structure that describes certain problems solvable with a greedy algorithm. In either case, the mathematical structure implies that set inclusion defines partial order on K, interpretable as an educational prerequirement: if a(⪯)b in this partial order, then a must be learned before b. === Inner and outer fringe === The prerequisite partial order does not uniquely identify a curriculum; some concepts may lead to a variety of other possible topics. But the covering relation associated with the prerequisite partial does control curricular structure: if students know a before a lesson and b immediately after, then b must cover a in the partial order. In such a circumstance, the new topics covered between a and b constitute the outer fringe of a ("what the student was ready to learn") and the inner fringe of b ("what the student just learned"). == Construction of knowledge spaces == In practice, there exist several methods to construct knowledge spaces. The most frequently used method is querying experts. There exist several querying algorithms that allow one or several experts to construct a knowledge space by answering a sequence of simple questions. Another method is to construct the knowledge space by explorative data analysis (for example by item tree analysis) from data. A third method is to derive the knowledge space from an analysis of the problem solving processes in the corresponding domain.
Read more →
Zeuthen strategy

The Zeuthen strategy in cognitive science is a negotiation strategy used by some artificial agents. Its purpose is to measure the willingness to risk conflict. An agent will be more willing to risk conflict if it does not have much to lose in case that the negotiation fails. In contrast, an agent is less willing to risk conflict when it has more to lose. The value of a deal is expressed in its utility. An agent has much to lose when the difference between the utility of its current proposal and the conflict deal is high. When both agents use the monotonic concession protocol, the Zeuthen strategy leads them to agree upon a deal in the negotiation set. This set consists of all conflict free deals, which are individually rational and Pareto optimal, and the conflict deal, which maximizes the Nash product. The strategy was introduced in 1930 by the Danish economist Frederik Zeuthen. == Three key questions == The Zeuthen strategy answers three open questions that arise when using the monotonic concession protocol, namely: Which deal should be proposed at first? On any given round, who should concede? In case of a concession, how much should the agent concede? The answer to the first question is that any agent should start with its most preferred deal, because that deal has the highest utility for that agent. The second answer is that the agent with the smallest value of Risk(i,t) concedes, because the agent with the lowest utility for the conflict deal profits most from avoiding conflict. To the third question, the Zeuthen strategy suggests that the conceding agent should concede just enough raise its value of Risk(i,t) just above that of the other agent. This prevents the conceding agent to have to concede again in the next round. == Risk == Risk ( i , t ) = { 1 U i ( δ ( i , t ) ) = 0 U i ( δ ( i , t ) ) − U i ( δ ( j , t ) ) U i ( δ ( i , t ) ) otherwise {\displaystyle {\text{Risk}}(i,t)={\begin{cases}1&U_{i}(\delta (i,t))=0\\{\frac {U_{i}(\delta (i,t))-U_{i}(\delta (j,t))}{U_{i}(\delta (i,t))}}&{\text{otherwise}}\end{cases}}} Risk(i,t) is a measurement of agent i's willingness to risk conflict. The risk function formalizes the notion that an agent's willingness to risk conflict is the ratio of the utility that agent would lose by accepting the other agent's proposal to the utility that agent would lose by causing a conflict. Agent i is said to be using a rational negotiation strategy if at any step t + 1 that agent i sticks to his last proposal, Risk(i,t) > Risk(j,t). == Sufficient concession == If agent i makes a sufficient concession in the next step, then, assuming that agent j is using a rational negotiation strategy, if agent j does not concede in the next step, he must do so in the step after that. The set of all sufficient concessions of agent i at step t is denoted SC(i, t). == Minimal sufficient concession == δ ′ = arg ⁡ max δ ∈ S C ( A , t ) { U A ( δ ) } {\displaystyle \delta '=\arg \max _{\delta \in {SC(A,t)}}\{U_{A}(\delta )\}} is the minimal sufficient concession of agent A in step t. Agent A begins the negotiation by proposing δ ( A , 0 ) = arg ⁡ max δ ∈ N S U A ( δ ) {\displaystyle \delta (A,0)=\arg \max _{\delta \in {NS}}U_{A}(\delta )} and will make the minimal sufficient concession in step t + 1 if and only if Risk(A,t) ≤ Risk(B,t). Theorem If both agents are using Zeuthen strategies, then they will agree on δ = arg ⁡ max δ ′ ∈ N S { π ( δ ′ ) } , {\displaystyle \delta =\arg \max _{\delta '\in {NS}}\{\pi (\delta ')\},} that is, the deal which maximizes the Nash product. Proof Let δA = δ(A,t). Let δB = δ(B,t). According to the Zeuthen strategy, agent A will concede at step t {\displaystyle t} if and only if R i s k ( A , t ) ≤ R i s k ( B , t ) . {\displaystyle Risk(A,t)\leq Risk(B,t).} That is, if and only if U A ( δ A ) − U A ( δ B ) U A ( δ A ) ≤ U B ( δ B ) − U B ( δ A ) U B ( δ B ) {\displaystyle {\frac {U_{A}(\delta _{A})-U_{A}(\delta _{B})}{U_{A}(\delta _{A})}}\leq {\frac {U_{B}(\delta _{B})-U_{B}(\delta _{A})}{U_{B}(\delta _{B})}}} U B ( δ B ) ( U A ( δ A ) − U A ( δ B ) ) ≤ U A ( δ A ) ( U B ( δ B ) − U B ( δ A ) ) {\displaystyle U_{B}(\delta _{B})(U_{A}(\delta _{A})-U_{A}(\delta _{B}))\leq U_{A}(\delta _{A})(U_{B}(\delta _{B})-U_{B}(\delta _{A}))} U A ( δ A ) U B ( δ B ) − U A ( δ B ) U B ( δ B ) ≤ U A ( δ A ) U B ( δ B ) − U A ( δ A ) U B ( δ A ) {\displaystyle U_{A}(\delta _{A})U_{B}(\delta _{B})-U_{A}(\delta _{B})U_{B}(\delta _{B})\leq U_{A}(\delta _{A})U_{B}(\delta _{B})-U_{A}(\delta _{A})U_{B}(\delta _{A})} − U A ( δ B ) U B ( δ B ) ≤ − U A ( δ A ) U B ( δ A ) {\displaystyle -U_{A}(\delta _{B})U_{B}(\delta _{B})\leq -U_{A}(\delta _{A})U_{B}(\delta _{A})} U A ( δ A ) U B ( δ A ) ≤ U A ( δ B ) U B ( δ B ) {\displaystyle U_{A}(\delta _{A})U_{B}(\delta _{A})\leq U_{A}(\delta _{B})U_{B}(\delta _{B})} π ( δ A ) ≤ π ( δ B ) {\displaystyle \pi (\delta _{A})\leq \pi (\delta _{B})} Thus, Agent A will concede if and only if δ A {\displaystyle \delta _{A}} does not yield the larger product of utilities. Therefore, the Zeuthen strategy guarantees a final agreement that maximizes the Nash Product.
Read more →
Learning vector quantization

In computer science, learning vector quantization (LVQ) is a prototype-based supervised classification algorithm. LVQ is the supervised counterpart of vector quantization systems. LVQ can be understood as a special case of an artificial neural network, more precisely, it applies a winner-take-all Hebbian learning-based approach. It is a precursor to self-organizing maps (SOM) and related to neural gas and the k-nearest neighbor algorithm (k-NN). LVQ was invented by Teuvo Kohonen. == Definition == An LVQ system is represented by prototypes W = ( w ( i ) , . . . , w ( n ) ) {\displaystyle W=(w(i),...,w(n))} which are defined in the feature space of observed data. In winner-take-all training algorithms one determines, for each data point, the prototype which is closest to the input according to a given distance measure. The position of this so-called winner prototype is then adapted, i.e. the winner is moved closer if it correctly classifies the data point or moved away if it classifies the data point incorrectly. An advantage of LVQ is that it creates prototypes that are easy to interpret for experts in the respective application domain. LVQ systems can be applied to multi-class classification problems in a natural way. A key issue in LVQ is the choice of an appropriate measure of distance or similarity for training and classification. Recently, techniques have been developed which adapt a parameterized distance measure in the course of training the system, see e.g. (Schneider, Biehl, and Hammer, 2009) and references therein. LVQ can be a valuable aid in classifying text documents. == Algorithm == The algorithms are presented as in. Set up: Let the data be denoted by x i ∈ R D {\displaystyle x_{i}\in \mathbb {R} ^{D}} , and their corresponding labels by y i ∈ { 1 , 2 , … , C } {\displaystyle y_{i}\in \{1,2,\dots ,C\}} . The complete dataset is { ( x i , y i ) } i = 1 N {\displaystyle \{(x_{i},y_{i})\}_{i=1}^{N}} . The set of code vectors is w j ∈ R D {\displaystyle w_{j}\in \mathbb {R} ^{D}} . The learning rate at iteration step t {\displaystyle t} is denoted by α t {\displaystyle \alpha _{t}} . The hyperparameters w {\displaystyle w} and ϵ {\displaystyle \epsilon } are used by LVQ2 and LVQ3. The original paper suggests ϵ ∈ [ 0.1 , 0.5 ] {\displaystyle \epsilon \in [0.1,0.5]} and w ∈ [ 0.2 , 0.3 ] {\displaystyle w\in [0.2,0.3]} . === LVQ1 === Initialize several code vectors per label. Iterate until convergence criteria is reached. Sample a datum x i {\displaystyle x_{i}} , and find out the code vector w j {\displaystyle w_{j}} , such that x i {\displaystyle x_{i}} falls within the Voronoi cell of w j {\displaystyle w_{j}} . If its label y i {\displaystyle y_{i}} is the same as that of w j {\displaystyle w_{j}} , then w j ← w j + α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}+\alpha _{t}(x_{i}-w_{j})} , otherwise, w j ← w j − α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\alpha _{t}(x_{i}-w_{j})} . === LVQ2 === LVQ2 is the same as LVQ3, but with this sentence removed: "If w j {\displaystyle w_{j}} and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, then w j ← w j − α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\alpha _{t}(x_{i}-w_{j})} and w k ← w k + α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}+\alpha _{t}(x_{i}-w_{k})} .". If w j {\displaystyle w_{j}} and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, then nothing happens. === LVQ3 === Initialize several code vectors per label. Iterate until convergence criteria is reached. Sample a datum x i {\displaystyle x_{i}} , and find out two code vectors w j , w k {\displaystyle w_{j},w_{k}} closest to it. Let d j := ‖ x i − w j ‖ , d k := ‖ x i − w k ‖ {\displaystyle d_{j}:=\|x_{i}-w_{j}\|,d_{k}:=\|x_{i}-w_{k}\|} . If min ( d j d k , d k d j ) > s {\displaystyle \min \left({\frac {d_{j}}{d_{k}}},{\frac {d_{k}}{d_{j}}}\right)>s} , where s = 1 − w 1 + w {\displaystyle s={\frac {1-w}{1+w}}} , then If w j {\displaystyle w_{j}} and x i {\displaystyle x_{i}} have the same class, and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have different classes, then w j ← w j + α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}+\alpha _{t}(x_{i}-w_{j})} and w k ← w k − α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}-\alpha _{t}(x_{i}-w_{k})} . If w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, and w j {\displaystyle w_{j}} and x i {\displaystyle x_{i}} have different classes, then w j ← w j − α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\alpha _{t}(x_{i}-w_{j})} and w k ← w k + α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}+\alpha _{t}(x_{i}-w_{k})} . If w j {\displaystyle w_{j}} and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, then w j ← w j − ϵ α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\epsilon \alpha _{t}(x_{i}-w_{j})} and w k ← w k + ϵ α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}+\epsilon \alpha _{t}(x_{i}-w_{k})} . If w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have different classes, and w j {\displaystyle w_{j}} and x i {\displaystyle x_{i}} have different classes, then the original paper simply does not explain what happens in this case, but presumably nothing happens in this case. Otherwise, skip. Note that condition min ( d j d k , d k d j ) > s {\displaystyle \min \left({\frac {d_{j}}{d_{k}}},{\frac {d_{k}}{d_{j}}}\right)>s} , where s = 1 − w 1 + w {\displaystyle s={\frac {1-w}{1+w}}} , precisely means that the point x i {\displaystyle x_{i}} falls between two Apollonian spheres.
Read more →
Horovod (machine learning)

Horovod is a free and open-source distributed deep learning training framework for TensorFlow, Keras, PyTorch and Apache MXNet. It is designed to scale existing single-GPU training scripts to efficiently run on multiple GPUs and computer nodes with minimal code changes, using synchronous data-parallel training based on the ring-allreduce communication pattern. Horovod was initially developed at Uber and released as an open-source project in 2017, and is now hosted by the LF AI & Data Foundation, a project of the Linux Foundation. == History == Horovod was created at Uber as part of the company's internal machine learning platform Michelangelo to simplify scaling TensorFlow models across many GPUs. The first public release of the library, version 0.9.0, was tagged on GitHub in August 2017 under the Apache 2.0 licence. In October 2017, Uber Engineering publicly introduced Horovod as an open-source component of its deep learning toolkit. In February 2018 Alexander Sergeev and Mike Del Balso published a technical paper describing Horovod's design and benchmarking its performance on up to 512 GPUs, showing near-linear scaling for several image-classification models when compared with single-GPU baselines. In December 2018 Uber contributed Horovod to the LF Deep Learning Foundation (later LF AI & Data), making it a Linux Foundation project. Horovod entered incubation under LF AI & Data and graduated as a full foundation project in 2020. Since its initial release the project has expanded beyond TensorFlow to provide APIs for PyTorch, Keras and Apache MXNet, as well as integrations with frameworks such as Apache Spark and Ray, support for elastic training, and tooling for automated performance tuning and profiling. == Design and features == Horovod core principles are based on the MPI concepts size, rank, local rank, allreduce, allgather, broadcast, and alltoall. Horovod implements synchronous data-parallel training, in which each worker process maintains a replica of the model and computes gradients on different mini-batches of data. The gradients are aggregated across workers using the ring-allreduce communication pattern rather than a central parameter server, which reduces communication bottlenecks and can improve scaling on multi-GPU clusters. Communication is built on top of collective-communication libraries such as MPI, NCCL, Gloo and Intel oneCCL, and supports both GPU and CPU training. In the benchmark experiments reported in the original paper, Horovod achieved around 90% scaling efficiency on 512 GPUs for the ResNet-101 and Inception v3 convolutional neural networks, and around 68% scaling efficiency for the VGG-16 model. Horovod can be deployed on-premises or in cloud environments and is distributed as a Python package with optional GPU support via CUDA. The official documentation provides guides for running Horovod with Docker, Kubernetes (including via Kubeflow and the MPI Operator), commercial platforms such as Databricks, and cluster schedulers such as LSF. == Adoption and use cases == Within Uber, Horovod has been used for applications including autonomous driving research, fraud detection and trip forecasting. Major cloud providers have integrated Horovod into their managed machine learning offerings. Amazon Web Services supports distributed training with Horovod in services such as Amazon SageMaker and AWS Deep Learning Containers, while Microsoft Azure documents Horovod-based training workflows for Azure Synapse Analytics. Technical guides from academic and research computing centres, including Purdue University and the NASA Advanced Supercomputing programme, describe Horovod-based workflows for multi-GPU training on supercomputers and clusters. Horovod is also used in conjunction with Apache Spark and dedicated storage systems as part of end-to-end data processing and model-training pipelines. Industry blogs and technical tutorials describe deployments of Horovod on Kubernetes, on-premises clusters and cloud-managed Kubernetes services such as Amazon EKS.
Read more →