AI App That Can Edit Photos

AI App That Can Edit Photos — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Cleverbot

Cleverbot is a chatterbot web application. It was created by British AI scientist Rollo Carpenter and launched in October 2008. It was preceded by Jabberwacky, a chatbot project that began in 1988 and went online in 1997. In its first decade, Cleverbot held several thousand conversations with Carpenter and his associates. Since launching on the web, the number of conversations held has exceeded 150 million. Besides the web application, Cleverbot is also available as an iOS, Android, and Windows Phone app. == Operation == Cleverbot's responses are not pre-programmed because it learns from human input: Humans type into the box below the Cleverbot logo and the system finds all keywords or an exact phrase matching the input. After searching through its saved conversations, it responds to the input by finding how a human responded to that input when it was asked, in part or in full, by Cleverbot. Cleverbot participated in a formal Turing test at the 2011 Techniche festival at the Indian Institute of Technology Guwahati on 3 September 2011. Out of the 1334 votes cast, Cleverbot was judged to be 59.3% human, compared to the rating of 63.3% human achieved by human participants. A score of 50.05% or higher is often considered to be a passing grade. The software running for the event had to handle just 1 or 2 simultaneous requests, whereas online Cleverbot is usually talking to around 10,000 to 50,000 people at once. == Developments == Cleverbot is constantly growing in data size at the rate of 4 to 7 million interactions per day. Updates to the software have been mostly behind the scenes. In 2014, Cleverbot was upgraded to use GPU serving techniques. Unlike Eliza, the program does not respond in a fixed way, instead choosing its responses heuristically using fuzzy logic, the whole of the conversation being compared to the millions that have taken place before. Cleverbot now uses over 279 million interactions, about 3-4% of the data it has already accumulated. The developers of Cleverbot are attempting to build a new version using machine learning techniques. An app that uses the Cleverscript engine to play a game of 20 Questions has been launched under the name Clevernator. Unlike other such games, the player asks the questions and it is the role of the AI to understand, and answer factually. An app that allows owners to create and talk to their own small Cleverbot-like AI has been launched, called Cleverme! for Apple products. == In popular culture == Cleverbot received media attention after being featured in the popular 2010 creepypasta ARG web serial Ben Drowned by Alexander D. Hall. In early 2017, a Twitch stream of two Google Home devices modified to talk to each other using Cleverbot garnered over 700,000 visitors and over 30,000 peak concurrent viewers.
Read more →
Angel F

Angel_F is a fictional child artificial intelligence that has been used in art performances worldwide focused on the issues of digital liberties, intellectual property and on the evolution of language and behaviour in information society. The character was created by Salvatore Iaconesi in 2007 as a hack to the Biodoll art performance by Italian artist Franca Formenti. The project was later joined by Oriana Persico who curated communication and part of the theoretical approaches of the action. The Angel_F project has been featured in books, magazines, national televisions, and has been invited to many conferences and events, both academic and artistic. == Creation == Angel_F is a backronym which stands for Autonomous Non Generative E-volitive Life_Form. The project was born in 2007 and resulted from the fusion of two contemporary art performances. Franca Formenti, an Italian artist living in Varese, invented the Biodoll character in 2002, which began making its appearances first on the network and later in the physical world by using what were called "clones": young women, prostitutes, pornographic starlets, transsexuals and models interpreting the role of a digital prostitute. The Biodoll was an art performance focused on research emerging from the network of new forms of sexualities, and on the analysis of changes brought on by this transformation to the concepts of private and public spaces, privacy, and the possibility of creating multiple fluid identities through language and digital media. The theme of fertility has always been central to the Biodoll performance: the digital prostitute was a wombless clone but desired giving birth to a son, the 'Bloki'. In a process starting in 2006, and ending in February 2007, Salvatore Iaconesi (xDxD.vs.xDxD) used his 'Talker' linguistic artificial intelligence to animate the digital child conceived with prof. Derrick de Kerckhove: Angel_F. Iaconesi and Persico met in November 2006 and immediately started collaborating on the birth of Angel_F. Angel_F was designed as a synthetic digital being composed through narrative, technological and cognitive psychology layers. The objective was to create iconic characteristics that resulted in being evocative and able to mimic human life up to a level in which bringing up a symbolic dialogue was possible. On the other side, the artificial identity was to implement and expose the cultural, emotional and relational ways that were typical of networked social ecosystems, among those technologies, systems and infrastructures that entered and shaped people's daily lives. The young digital being mimicked the evolution of a human baby: initially conceived inside the website of its digital mother it emulated the birth of a child by using the metaphor of a virus developing inside a website, taking progressively more space in the domain's databases and interfaces. Content was produced through the software by using small browser-based spyware techniques, through which Angel_F could infer the list of major portals that had been visited by the website's users. The Biodoll website was invaded by this growing presence and, thus, Angel_F was born. The Artificial Intelligence (AI) component of Angel_F was derived from another project, Talker, through which internet users could build up the AI's linguistic network by feeding it their text and web clips. Angel_F used this component to generate sentences and phrases, publishing them on the interface and on selected blogs. The parallel between the growth of the AI and that of a child kept building up and, just as children learn how to speak and act by observing their parents and the people around them, Angel_F used its spyware and AI components to learn, to navigate websites and web portals using web crawler based techniques, and to interact with other people by using the contents hosted and generated in its database to create surreal dialogues in blogs and websites. A virtual school was created, called Talker Mind, to narratively continue the AI's growth. Five professors (Massimo Canevacci, Antonio Caronia, Carlo Formenti, Derrick de Kerckhove and Luigi Pagliarini) fed their texts and academic articles to Angel_F, simulating virtual asynchronous lessons by using a multi-blog structure. A peer-to-peer system was also created at the time, named 'Presence'. Its interface resembled the one of 8-bit videogames and the peer to peer users travelled in a starry space and were able to perform standard Instant Messaging tasks, such as chat and file sharing. The interactions were possible both among humans and digital beings. Angel_F was the first user of the Presence peer to peer system. Angel_F entered the physical world as a baby-stroller mounted laptop computer that was used to let the digital child join events and conferences held worldwide. == Events == Angel_F performed all over the world, both in artistic contexts and in academic ones. It was also used for the communication strategy of several activist groups on the themes of intellectual property and digital freedoms. The first public space performance was held in Milan, when the Biodoll distributed a generative free press publication (called the Bloki FreePreXXX, its text was generated algorithmically and inserted into a prepared graphic layout). June 14, 2007: The second performance was held in Rome, at the Forte Prenestino, with a massive playroom created through computational graphics that people could interact with and that were generated by the AI. June 22, 2007: Angel_F presented the closing remarks for an Ipotesi per Assurdo (Absurd Hypothesis) with Salvatore Iaconesi and Oriana Persico at the IULM University in Milan, discussing the possibilities for an ecosystemic, sustainable reinvention of corporations. July 28, 2007: Hundreds of people at LiberaFesta (Free Party) in Rome listened to Angel_F in a speech discussing new politics and hacker ethics. 2007: The Glocal & Outsiders conference held in Prague at the Academy of Sciences was the first academic presentation of the Angel_F project, together with the Biodoll. September 2007: Angel_F was not allowed to post its contribution to the DFIR (Dialogue Forum for Internet Rights) held in Rome in preparation for Rio de Janeiro's Internet Governance Forum (IGF) edition. The case quickly turned into a collaboration among the involved parties and Angel_F was invited to the global event in Brazil where it was the only digital being present. Angel_F contributed a videomessage, in the digital freedoms workshop, which suggested some ideas for action to the United Nations and to all the parties involved in the IGF organization. October 2007: Angel_F was presented live at the FE/MALE 2 event, as an example of an atypical family during a public debate on new sexualities and social change. October 2007: Angel_F made a series of public performances Florence's Festival della Creatività (Festival of Creativity), an institutional event held periodically to showcase Italy's and other countries' best technological projects. During the festival Derrick de Kerckhove publicly recognized the little AI as his digital son. December 2007: Several international associations, and scientific researchers had been involved with Angel_F, eventually producing the system and process used to set up the Talker Mind digital school for the AI with Angel_F's professors. March 2008: The Tecnológico de Monterrey university in Mexico City organized the Computer Art Congress 2 international event, featuring Angel_F's project among with the ones by scientific researchers worldwide. July 2008: The project was presented in Austria at the Planetary Collegium's Consciousness Reframed 9 conference, together with the 'NeoRealismo Virtuale'. October 2008: Angel_F was used at a public event on a European scale called Freedom not Fear discussing privacy and civil liberties. July 2009: Angel_F has been seen with its digital father Derrick de Kerckhove to protest against Italy's harsh politics on freedom of speech. The project concluded in 2009 with the publication of a book entitled 'Angel F. Diario di una intelligenza artificiale' (Angel_F, the diaries of an Artificial Intelligence).
Read more →
Geopolitical ontology

The FAO geopolitical ontology is an ontology developed by the Food and Agriculture Organization of the United Nations (FAO) to describe, manage and exchange data related to geopolitical entities such as countries, territories, regions and other similar areas. == Definitions and examples == An ontology is a kind of dictionary that describes information in a certain domain using concepts and relationships. It is often implemented using OWL (Web Ontology Language), an XML-based standard language that can be interpreted by computers. A Concept is defined as abstract knowledge. For example, in the geopolitical ontology a non-self-governing territory and a geographical group are concepts. Concepts are explicitly implemented in the ontology with individuals and classes: An individual is defined as an object perceived from the real world. In the geopolitical domain Ethiopia and the least developed countries group are individuals. A class is defined as a set of individuals sharing common properties. In the geopolitical domain, Ethiopia, Republic of Korea and Italy are individuals of the class self-governing territory; and least developed countries is an individual of the class special group. Relationships between concepts are explicitly implemented by: Object properties between individuals of two classes. For example, has member and is in group properties, as shown in Figure 1. Datatype properties between individuals and literals or XML datatypes. For example, the individual Afghanistan has the datatype property CodeISO3 with the value "AFG". Restrictions in classes and/or properties. For example, the property official English name of the class self-governing territory has been restricted to have only one value, this means that a self-governing territory (or country) can only have one internationally recognized official English name. The advantage of describing information in an ontology is that it enables to acquire domain knowledge by defining hierarchical structures of classes, adding individuals, setting object properties and datatype properties, and assigning restrictions. == FAO ontology == The geopolitical ontology provides names in seven languages (Arabic, Chinese, French, English, Spanish, Russian and Italian) and identifiers in various international coding systems (ISO2, ISO3, AGROVOC, FAOSTAT, FAOTERM, GAUL, UN, UNDP and DBPediaID codes) for territories and groups. Moreover, the FAO geopolitical ontology tracks historical changes from 1985 up until today; provides geolocation (geographical coordinates); implements relationships among countries and countries, or countries and groups, including properties such as has border with, is predecessor of, is successor of, is administered by, has members, and is in group; and disseminates country statistics including country area, land area, agricultural area, GDP or population. The FAO geopolitical ontology provides a structured description of data sources. This includes: source name, source identifier, source creator and source's update date. Concepts are described using the Dublin Core vocabulary In summary, the main objectives of the FAO geopolitical ontology are: To provide the most updated geopolitical information (names, codes, relationships, statistics) To track historical changes in geopolitical information To improve information management and facilitate standardized data sharing of geopolitical information To demonstrate the benefits of the geopolitical ontology to improve interoperability of corporate information systems It is possible to download the FAO geopolitical ontology in OWL and RDF formats. Documentation is available in the FAO Country Profiles Geopolitical information web page. == Features of the FAO ontology == The geopolitical ontology contains : Area types: Territories: self-governing, non-self-governing, disputed, other. Groups: organizations, geographic, economic and special groups. Names (official, short and names for lists) in Arabic, Chinese, English, French, Spanish, Russian and Italian. International codes: UN code – M49, ISO 3166 Alpha-2 and Alpha-3, UNDP code, GAUL code, FAOSTAT, AGROVOC FAOTERM and DBPediaID. Coordinates: maximum latitude, minimum latitude, maximum longitude, minimum longitude. Basic country statistics: country area, land area, agricultural area, GDP, population. Currency names and codes. Adjectives of nationality. Relations: Groups membership. Neighbours (land border), administration of non-self-governing. Historic changes: predecessor, successor, valid since, valid until. == Implementation into OWL == The FAO geopolitical ontology is implemented in OWL. It consists of classes, properties, individuals and restrictions. Table 1 shows all classes, gives a brief description and lists some individuals that belong to each class. Note that the current version of the geopolitical ontology does not provide individuals of the class "disputed" territories. Table 2 and Table 3 illustrate datatype properties and object properties. == Geopolitical ontology in Linked Open Data == The FAO Geopolitical ontology is embracing the W3C Linked Open Data (LOD) initiative and released its RDF version of the geopolitical ontology in March 2011. The term 'Linked Open Data' refers to a set of best practices for publishing and connecting structured data on the Web. The key technologies that support Linked Data are URIs, HTTP and RDF. The RDF version of the geopolitical ontology is compliant with all Linked data principles to be included in the Linked Open Data cloud, as explained in the following. == Resolvable http:// URIs == Every resource in the OWL format of the FAO Geopolitical Ontology has a unique URI. Dereferenciation was implemented to allow for three different URIs to be assigned to each resource as follows: URI identifying the non-information resource Information resource with an RDF/XML representation Information resource with an HTML representation In addition the current URIs used for OWL format needed to be kept to allow for backwards compatibility for other systems that are using them. Therefore, the new URIs for the FAO Geopolitical Ontology in LOD were carefully created, using “Cool URIs for Semantic Web” and considering other good practices for URIs, such as DBpedia URIs. == New URIs == The URIs of the geopolitical ontology need to be permanent, consequently all transient information, such as year, version, or format was avoided in the definition of the URIs. The new URIs can be accessed For example, for the resource “Italy” the URIs are the following: http://www.fao.org/countryprofiles/geoinfo/geopolitical/resource/Italy identifies the non-information resource. http://www.fao.org/countryprofiles/geoinfo/geopolitical/data/Italy identifies the resource with an RDF/XML representation. http://www.fao.org/countryprofiles/geoinfo/geopolitical/page/Italy identifies the information resource with an HTML representation. In addition, “owl:sameAs” is used to map the new URIs to the OWL representation. == Dereferencing URIs == When a non-information resource is looked up without any specific representation format, then the server needs to redirect the request to information resource with an HTML representation. For example, to retrieve the resource “Italy”, which is a non-information resource, the server redirects to the HTML page of “Italy”. == At least 1000 triples in the datasets == The total number of triple statements in FAO Geopolitical Ontology is 22,495. At least 50 links to a dataset already in the current LOD Cloud: FAO Geopolitical Ontology has 195 links to DBpedia, which is already part of the LOD Cloud. == Access to the entire dataset == FAO Geopolitical Ontology provides the entire dataset as a RDF dump. The RDF version of the FAO Geopolitical Ontology has been already registered in CKAN and it was requested to add it into the LOD Cloud. == Example of use == The FAO Country Profiles is an information retrieval tool which groups the FAO's vast archive of information on its global activities in agriculture and rural development in one single area and catalogues it exclusively by country. The FAO Country Profiles system provides access to country-based heterogeneous data sources. By using the geopolitical ontology in the system, the following benefits are expected: Enhanced system functionality for content aggregation and synchronization from the multiple source repositories. Improved information access and browsing through comparison of data in neighbor countries and groups. Figure 3 shows a page in the FAO Country Profiles where the geopolitical ontology is described.
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 →
Microapp

A microapp is a super-specialized application designed to perform one task or use case with the only objective of doing it well. They follow the single responsibility principle, which states that "a class should have one and only one reason to change." Micro applications help developers create less complex applications while reducing costs by breaking down monolithic systems into groups of independent services acting as one system. A good example of Microapps would be https://docs.citrix.com/en-us/legacy-archive/downloads/microapps.pdfthat provide single purpose action from Salesforce and over 40 applications on its workspace. == Requirements and characteristics == Microapps usually are accessible on any device, display, or operating system without installation on the viewer's device. To qualify as a microapp, the entity must: be built and deployed as an independent software module bring together various media types into a single experience have advanced security and compliance features be functionally-extensible comply with granular data demands be agnostic single use case oriented Microapps differentiate from traditional web or mobile applications by how the end-user interacts with them. Consequently, they can be embedded in websites or viewed online to bypass app stores and are typically built to provide a focused experience to the user. == Usage == Microapps are typically used for commercial purposes to reduce development costs for projects not requiring the large scope of a traditional web or mobile application. In addition, they are often used to showcase in-depth information or enrich marketing material with interactivity. Lately, micro apps are being used to boost productivity by providing quick tools to people to reuse best practices. Users have been interacting with microapps for a while with suites like Microsoft 365 and Google Workspace, where each one of their end-user services could be considered as a microapp. All these microapps share a unique identity manager to provide a unified user experience. == Benefits == Replacing monolith systems with microapps provide several advantages like: Reduce complexity for developers and users. Smaller, more cohesive, and maintainable codebases Scalable organizations with decoupled, autonomous teams Allows for hyper-specialization Independent deployment Multi-stack == Cloud-native microapps == Technologies like Kubernetes, or OpenShift, allow companies to replace their monolith and legacy systems with modular software taking advantage of microapps on reducing costs and improve reliability and security. == Microapps vs. microservices == There is a widespread misunderstanding between these two concepts, which is the key difference. Microservices is an architectural style that is systems-centric, meaning it decouples the presentation and data layer using web services APIs. On the other side, micro apps behave more as a super-architecture style (that embraces microservices among other types), and it is user-centric, meaning they decouple the whole monolith system onto modules that are designed to interact with final users. Both architectural styles rely on modularity to provide high performance, scalability, and resilience. == Considerations == Developing Micro apps requires a different approach than traditional software, and user experience is crucial. The following considerations are essential for switching to microapps. To run multiple microapps is required a single identity management system. Microservices are well suited to make microapps more powerful Apps with different levels of maturity might create a non-unified user experience. Duplication of dependencies can create security issues and inefficiencies. Suitable for well-organized teams
Read more →
AgMES

The AgMES (Agricultural Metadata Element set) initiative was developed by the Food and Agriculture Organization (FAO) of the United Nations and aims to encompass issues of semantic standards in the domain of agriculture with respect to description, resource discovery, interoperability, and data exchange for different types of information resources. There are numerous other metadata schemas for different types of information resources. The following list contains a list of a few examples: Document-like Information Objects (DLIOs): Dublin Core, Agricultural Metadata Element Set (AgMES) Events: VCalendar Geographic and Regional Information: Geographic information—Metadata ISO/IEC 11179 Standards Persons: Friend-of-a-friend (FOAF), vCard Plant Production and Protection: Darwin Core (1.0 and 2.0) (DwC) AgMES as a namespace is designed to include agriculture specific extensions for terms and refinements from established standard metadata namespaces like Dublin Core, AGLS etc. Thus, to be used for Document-like Information Objects, for example like publications, articles, books, web sites, papers, etc., it will have to be used in conjunction with the standard namespaces mentioned before. The AgMES initiative strives to achieve improved interoperability between information resources in agricultural domain by enabling means for exchange of information. Describing a DLIO with AgMES means exposing its major characteristics and contents in a standard way that can be reused easily in any information system. The more institutions and organizations in the agricultural domain that use AgMES to describe their DLIOs, the easier it will be to interchange data in between information systems like digital libraries and other repositories of agricultural information. == Use of AgMES == Metadata on agricultural Document-like Information Objects (DLIOs) can be created and stored in various formats: embedded in a web site (in the manner as with the HTML meta tag) in a separate metadata database in an XML file in an RDF file AgMES defines elements that can be used to describe a DLIO that can be used together with other metadata standards such as the Dublin Core, the Australian Government Locator Service. A complete list of all elements, refinements and schemes endorsed by AgMES is available from the AgMES website. === Creating application profiles === Application profiles are defined as schemas which consist of data elements drawn from one or more namespaces, combined by implementers, and optimized for a particular local application. Application profiles share the following four characteristics: They draw upon existing pool of metadata definition standards to extract suitable application- or requirement oriented elements. An application profile cannot create new elements. Application profiles specify the application specific details such as the schemes or controlled vocabularies. An application profile also contains information such as the format for the element value, cardinality or data type. Lastly, an application profile can refine standardized definitions as long as it is "semantically narrower or more specific". This capability of application profiles caters to situations where a domain specific terminology is needed to replace a more general one. === Sample application profiles using AgMES === The AGRIS Application Profile is a standard created specifically to enhance the description, exchange and subsequent retrieval of agricultural Document-like Information Objects (DLIOs). It is a format that allows sharing of information across dispersed bibliographic systems and is based on well-known and accepted metadata standards. The Event Application Profile is a standard created to allow members of the Agricultural community to 'know' about an upcoming event and guide them to the event Web site where they can find further information. The information communicated is thus minimum yet interoperable across domains and organizations. == AgMES and the semantic web == One of the advantages of the AgMES metadata schema is the ability to link between the metadata element and controlled vocabularies. The use of controlled vocabulary provides a "known" set of options to the indexer (and the search programmer) as to how the field can be filled out. Often the values may come from a specific thesaurus (e.g. AGROVOC) or classification schemes (e.g. the AGRIS/CARIS classification scheme) etc. Thanks to the possibility to use controlled vocabularies for metadata elements, the user is provided with the most precise information. In this context, work is also being carried out on exploiting the power of controlled vocabularies expressed as using URIs and machine-understandable semantics. In this context, FAO is promoting the Agricultural Ontology Service (AOS) initiative with the objective of expressing more semantics within the traditional thesaurus AGROVOC and build a Concept Server as a repository from which it will be always possible to extract traditional KOS.
Read more →
Feigenbaum test

A Feigenbaum test is a variation of the Turing test where a computer system attempts to replicate an expert in a given field such as chemistry or marketing. It is also known, as a subject matter expert Turing test and was proposed by Edward Feigenbaum in a 2003 paper. The concept is also described by Ray Kurzweil in his 2005 book The Singularity is Near. Kurzweil argues that machines who pass this test are an inevitable consequence of Moore's Law.
Read more →
RuleML

RuleML is a global initiative, led by a non-profit organization RuleML Inc., that is devoted to advancing research and industry standards design activities in the technical area of rules that are semantic and highly inter-operable. The standards design takes the form primarily of a markup language, also known as RuleML. The research activities include an annual research conference, the RuleML Symposium, also known as RuleML for short. Founded in fall 2000 by Harold Boley, Benjamin Grosof, and Said Tabet, RuleML was originally devoted purely to standards design, but then quickly branched out into the related activities of coordinating research and organizing an annual research conference starting in 2002. The M in RuleML is sometimes interpreted as standing for Markup and Modeling. The markup language was developed to express both forward (bottom-up) and backward (top-down) rules in XML for deduction, rewriting, and further inferential-transformational tasks. It is defined by the Rule Markup Initiative, an open network of individuals and groups from both industry and academia that was formed to develop a canonical Web language for rules using XML markup and transformations from and to other rule standards/systems. Markup standards and initiatives related to RuleML include: Rule Interchange Format (RIF): The design and overall purpose of W3C's Rule Interchange Format (RIF) industry standard is based primarily on the RuleML industry standards design. Like RuleML, RIF embraces a multiplicity of potentially useful rule dialects that nevertheless share common characteristics. RuleML Technical Committee from Oasis-Open: An industry standards effort devoted to legal automation utilizing RuleML. Semantic Web Rule Language (SWRL): An industry standards design, based primarily on an early version of RuleML, whose development was funded in part by the DARPA Agent Markup Language (DAML) research program. Semantic Web Services Framework, particularly its Semantic Web Services Language: An industry standards design, based primarily on a medium-mature version of RuleML, whose development was funded in part by the DARPA Agent Markup Language (DAML) research program and the WSMO research effort of the EU. Mathematical Markup Language (MathML): However, MathML's Content Markup is better suited for defining functions rather than relations or general rules Predictive Model Markup Language (PMML): With this XML-based language one can define and share various models for data-mining results, including association rules Attribute Grammars in XML (AG-markup): For AG's semantic rules, there are various possible XML markups that are similar to Horn-rule markup Extensible Stylesheet Language Transformations (XSLT): This is a restricted term-rewriting system of rules, written in XML, for transforming XML documents into other text documents
Read more →
Cloud load balancing

Cloud load balancing is a type of load balancing that is performed in cloud computing. Cloud load balancing is the process of distributing workloads across multiple computing resources. Cloud load balancing reduces costs associated with document management systems and maximizes availability of resources. It is a type of load balancing and not to be confused with Domain Name System (DNS) load balancing. While DNS load balancing uses software or hardware to perform the function, cloud load balancing uses services offered by various computer network companies. == Comparison With DNS load balancing == Cloud load balancing has an advantage over DNS load balancing as it can transfer loads to servers globally as opposed to distributing it across local servers. In the event of a local server outage, cloud load balancing delivers users to the closest regional server without interruption for the user. Cloud load balancing addresses issues relating to TTL reliance present during DNS load balancing. DNS directives can only be enforced once in every TTL cycle and can take several hours if switching between servers during a lag or server failure. Incoming server traffic will continue to route to the original server until the TTL expires and can create an uneven performance as different internet service providers may reach the new server before other internet service providers. Another advantage is that cloud load balancing improves response time by routing remote sessions to the best performing data centers. == Importance of Load Balancing == Cloud computing brings advantages in "cost, flexibility and availability of service users." Those advantages drive the demand for Cloud services. The demand raises technical issues in Service Oriented Architectures and Internet of Services (IoS)-style applications, such as high availability and scalability. As a major concern in these issues, load balancing allows cloud computing to "scale up to increasing demands" by efficiently allocating dynamic local workload evenly across all nodes. == Load Balancing Techniques == === Scheduling Algorithms === Opportunistic Load Balancing (OLB) is the algorithm that assigns workloads to nodes in free order. It is simple but does not consider the expected execution time of each node. Load balance Min-Min (LBMM) assigns sub-tasks to the node which requires minimum execution time. === Load Balancing Policies === Workload and Client Aware Policy (WCAP) specifies the unique and special property (USP) of requests and computing nodes. With the information of USP, the schedule can decide the most suitable node to complete a request. WCAP makes the most of computing nodes by reducing their idle time. Also, it reduces performance time through searches based on content information. === A Comparative Study of Algorithms === Biased Random Sampling bases its job allocation on the network represented by a directed graph. For each execution node in this graph, in-degree means available resources and out-degree means allocated jobs. In-degree will decrease during job execution while out-degree will increase after job allocation. Active Clustering is a self-aggregation algorithm to rewire the network. The experiment result is that"Active Clustering and Random Sampling Walk predictably perform better as the number of processing nodes is increased" while the Honeyhive algorithm does not show the increasing pattern. == Client-side Load Balancer Using Cloud Computing == Load balancer forwards packets to web servers according to different workloads on servers. However, it is hard to implement a scalable load balancer because of both the "cloud's commodity business model and the limited infrastructure control allowed by cloud providers." Client-side Load Balancer (CLB) solve this problem by using a scalable cloud storage service. CLB allows clients to choose back-end web servers for dynamic content although it delivers static content.
Read more →
Retrieval-based Voice Conversion

Retrieval-based Voice Conversion (RVC) is an open source voice conversion AI algorithm that enables realistic speech-to-speech transformations, accurately preserving the intonation and audio characteristics of the original speaker. == Overview == In contrast to text-to-speech systems such as ElevenLabs, RVC differs by providing speech-to-speech outputs instead. It maintains the modulation, timbre and vocal attributes of the original speaker, making it suitable for applications where emotional tone is crucial. The algorithm enables both pre-processed and real-time voice conversion with low latency. This real-time capability marks a significant advancement over previous AI voice conversion technologies, such as So-vits SVC. Its speed and accuracy have led many to note that its generated voices sound near-indistinguishable from "real life", provided that sufficient computational specifications and resources (e.g., a powerful GPU and ample RAM) are available when running it locally and that a high-quality voice model is used. == Technical foundation == Retrieval-based Voice Conversion (RVC) utilizes a hybrid approach that integrates feature extraction with retrieval-based synthesis. Instead of directly mapping source speaker features to the target speaker using statistical models, RVC retrieves relevant segments from a target speech database, aiming to enhance the naturalness and speaker fidelity of the converted speech. At a high level, the RVC system typically comprises three main components: (1) a content feature extractor, such as a phonetic posteriorgram (PPG) encoder or self-supervised models like HuBERT; (2) a vector retrieval module that searches a target voice database for the most similar speech units; and (3) a vocoder or neural decoder that synthesizes waveform output from the retrieved representations. The retrieval-based paradigm aims to mitigate the oversmoothing effect commonly observed in fully neural sequence-to-sequence models, potentially leading to more expressive and natural-sounding speech. Furthermore, with the incorporation of high-dimensional embeddings and k-nearest-neighbor search algorithms, the model can perform efficient matching across large-scale databases without significant computational overhead. Recent RVC frameworks have incorporated adversarial learning strategies and GAN-based vocoders, such as HiFi-GAN, to enhance synthesis quality. These integrations have been shown to produce clearer harmonics and reduce reconstruction errors. == Research developments == Research on RVC has recently explored the use of self-supervised learning (SSL) encoders such as wav2vec 2.0 and HuBERT to replace hand-engineered features like MFCCs. These encoders improve content preservation, especially when source and target speakers have dissimilar speaking styles or accents. Moreover, modern RVC models leverage vector quantization methods to discretize the acoustic space, improving both synthesis accuracy and generalization across unseen speakers. For example, retrieval-augmented VQ models can condition the synthesis stage on quantized speech tokens, which enhances controllability and style transfer. Despite its strengths, RVC still faces limitations related to database coverage, especially in real-time or few-shot settings. Inadequate diversity in the target voice corpus may lead to suboptimal retrieval or unnatural prosody. These advances demonstrate the viability of RVC as a strong alternative to conventional deep learning VC systems, balancing both flexibility and efficiency in diverse voice synthesis applications. == Training process == The training pipeline for retrieval-based voice conversion typically includes a preprocessing step where the target speaker's dataset is segmented and normalized. A pitch extractor such as librosa or DDSP-DDC may be used to obtain fundamental frequency (F0) features. During training, the model learns to map content features from the source speaker to the acoustic representation of the target speaker while maintaining pitch and prosody. The training objective often combines reconstruction loss with feature consistency loss across intermediate layers, and may incorporate cycle consistency loss to preserve speaker identity. Fine-tuning on small datasets is feasible due to the use of pre-trained models, particularly for the SSL encoder and content extractor components. This approach allows transfer learning to be applied effectively, enabling the model to converge faster and generalize better to unseen inputs. Most open implementations support batch training, gradient accumulation, and mixed-precision acceleration (e.g., FP16), especially when utilizing NVIDIA CUDA-enabled GPUs. == Real-time deployment == RVC systems can be deployed in real-time scenarios through WebUI interfaces and streaming audio frameworks. Optimizations include converting the inference graph to ONNX or TensorRT formats, reducing latency. Audio buffers are typically processed in chunks of 0.2–0.5 seconds to ensure minimal delay and seamless conversion. Cross-platform compatibility with tools such as OBS Studio and Voicemeeter enables integration into live streaming, video production, or virtual avatar environments. == Applications and concerns == The technology enables voice changing and mimicry, allowing users to create accurate models of others using only a negligible amount of minutes of clear audio samples. These voice models can be saved as .pth (PyTorch) files. While this capability facilitates numerous creative applications, it has also raised concerns about potential misuse as deepfake software for identity theft and malicious impersonation through voice calls. == Ethical and legal considerations == As with other deep generative models, the rise of RVC technology has led to increasing debate about copyright, consent, and authorship. While some jurisdictions may allow parody or fair use in creative contexts, impersonating living individuals without permission may infringe upon privacy and likeness rights. As a result, some platforms have begun issuing takedown notices against AI-generated voice content that closely mimics celebrities or musicians. === In pop culture === RVC inference has been used to create realistic depictions of song covers, such as replacing original vocals with characters like Twilight Sparkle and Mordecai to have them sing duets of popular music like "Airplanes" and "Somebody That I Used to Know." These AI-generated covers, which can sound strikingly similar to the voice imitated, have gained popularity on platforms like YouTube as humorous memes.
Read more →
Kinect

Kinect is a discontinued line of motion sensing input devices produced by Microsoft and first released in 2010. The devices generally contain RGB cameras, and infrared projectors and detectors that map depth through either structured light or time of flight calculations, which can in turn be used to perform real-time gesture recognition and body skeletal detection, among other capabilities. They also contain microphones that can be used for speech recognition and voice control. Kinect was originally developed as a motion controller peripheral for Xbox video game consoles, distinguished from competitors (such as Nintendo's Wii Remote and Sony's PlayStation Move) by not requiring physical controllers. The first-generation Kinect was based on technology from Israeli company PrimeSense, and unveiled at E3 2009 as a peripheral for Xbox 360 codenamed "Project Natal". It was first released on November 4, 2010, and would go on to sell eight million units in its first 60 days of availability. The majority of the games developed for Kinect were casual, family-oriented titles, which helped to attract new audiences to Xbox 360, but did not result in wide adoption by the console's existing, overall userbase. As part of the 2013 unveiling of Xbox 360's successor, Xbox One, Microsoft unveiled a second-generation version of Kinect with improved tracking capabilities. Microsoft also announced that Kinect would be a required component of the console, and that it would not function unless the peripheral is connected. The requirement proved controversial among users and critics due to privacy concerns, prompting Microsoft to backtrack on the decision. However, Microsoft still bundled the new Kinect with Xbox One consoles upon their launch in November 2013. A market for Kinect-based games still did not emerge after the Xbox One's launch; Microsoft would later offer Xbox One hardware bundles without Kinect included, and later revisions of the console removed the dedicated ports used to connect it (requiring a powered USB adapter instead). Microsoft ended production of Kinect for Xbox One in October 2017. Kinect has also been used as part of non-game applications in academic and commercial environments, as it was cheaper and more robust than other depth-sensing technologies at the time. While Microsoft initially objected to such applications, it later released software development kits (SDKs) for the development of Microsoft Windows applications that use Kinect. In 2020, Microsoft released Azure Kinect as a continuation of the technology integrated with the Microsoft Azure cloud computing platform. Part of the Kinect technology was also used within Microsoft's HoloLens project. Microsoft discontinued the Azure Kinect developer kits in October 2023. == History == === Development === The origins of the Kinect started around 2005, at a point where technology vendors were starting to develop depth-sensing cameras. Microsoft had been interested in a 3D camera for the Xbox line earlier but because the technology had not been refined, had placed it in the "Boneyard", a collection of possible technology they could not immediately work on. In 2005, Israeli company PrimeSense was founded by mathematicians and engineers to develop the "next big thing" for video games, incorporating cameras that were capable of mapping a human body in front of them and sensing hand motions. They showed off their system at the 2006 Game Developers Conference, where Microsoft's Alex Kipman, the general manager of hardware incubation, saw the potential in PrimeSense's technology for the Xbox system. Microsoft began discussions with PrimeSense about what would need to be done to make their product more consumer-friendly: not only improvements in the capabilities of depth-sensing cameras, but a reduction in size and cost, and a means to manufacture the units at scale was required. PrimeSense spent the next few years working at these improvements. Nintendo released the Wii in November 2006. The Wii's central feature was the Wii Remote, a handheld device that was detected by the Wii through a motion sensor bar mounted onto a television screen to enable motion controlled games. Microsoft felt pressure from the Wii, and began looking into depth-sensing in more detail with PrimeSense's hardware, but could not get to the level of motion tracking they desired. While they could determine hand gestures, and sense the general shape of a body, they could not do skeletal tracking. A separate path within Microsoft looked to create an equivalent of the Wii Remote, considering that this type of unit may become standardized similar to how two-thumbstick controllers became a standard feature. However, it was still ultimately Microsoft's goal to remove any device between the player and the Xbox. Kudo Tsunoda and Darren Bennett joined Microsoft in 2008, and began working with Kipman on a new approach to depth-sensing aided by machine learning to improve skeletal tracking. They internally demonstrated this and established where they believed the technology could be in a few years, which led to the strong interest to fund further development of the technology; this has also occurred at a time that Microsoft executives wanted to abandon the Wii-like motion tracking approach, and favored the depth-sensing solution to present a product that went beyond the Wii's capabilities. The project was greenlit by late 2008 with work started in 2009. The project was codenamed "Project Natal" after the Brazilian city Natal, Kipman's birthplace. Additionally, Kipman recognized the Latin origins of the word "natal" to mean "to be born", reflecting the new types of audiences they hoped to draw with the technology. Much of the initial work was related to ethnographic research to see how video game players' home environments were laid out, lit, and how those with Wiis used the system to plan how Kinect units would be used. The Microsoft team discovered from this research that the up-and-down angle of the depth-sensing camera would either need to be adjusted manually, or would require an expensive motor to move automatically. Upper management at Microsoft opted to include the motor despite the increased cost to avoid breaking game immersion. Kinect project work also involved packaging the system for mass production and optimizing its performance. Hardware development took around 22 months. During hardware development, Microsoft engaged with software developers to use Kinect. Microsoft wanted to make games that would be playable by families since Kinect could sense multiple bodies in front of it. One of the first internal titles developed for the device was the pack-in game Kinect Adventures developed by Good Science Studio that was part of Microsoft Studios. One of the game modes of Kinect Adventures was "Reflex Ridge", based on the Japanese Brain Wall game where players attempt to contort their bodies in a short time to match cutouts of a wall moving at them. This type of game was a key example of the type of interactivity they wanted with Kinect, and its development helped feed into the hardware improvements. Another development was Project Milo, a prototype game developed by Lionhead Studios led by Peter Molyneux where the player could interact with a virtual avatar through motion controls and voice recognition. Lionhead had developed the project based on original capabilities of the Kinect, but according to Molyneux, Microsoft had found that a consumer-grade version of the Kinect would cost thousands of dollars, so they scaled back the device and refocused the role of games for the Kinect to be more casual games as seen on the Wii. As a result, Project Milo no longer fit Microsoft's portfolio and was cancelled. Nearing the planned release, there was a problem of widespread testing of Kinect in various room types and different bodies accounting for age, gender, and race among other factors, while keeping the details of the unit confidential. Microsoft engaged in a company-wide program offering employees to take home Kinect units to test them. Microsoft also brought other non-gaming divisions, including its Microsoft Research, Microsoft Windows, and Bing teams to help complete the system. Microsoft established its own large-scale manufacturing facility to bulk product Kinect units and test them. === Introduction === Kinect was first announced to the public as "Project Natal" on June 1, 2009, during Microsoft's press conference at E3 2009; film director Steven Spielberg joined Microsoft's Don Mattrick to introduce the technology and its potential. Three demos were presented during the conference—Microsoft's Ricochet and Paint Party, and Lionhead Studios' Milo & Kate created by Peter Molyneux—while a Project Natal-enabled version of Criterion Games' Burnout Paradise was shown during the E3 exhibition. By E3 2009, the skeletal mapping technology was capable of simultaneously tracking four people, with a feature extraction of 4
Read more →
Leabra

Leabra stands for local, error-driven and associative, biologically realistic algorithm. It is a model of learning which is a balance between Hebbian and error-driven learning with other network-derived characteristics. This model is used to mathematically predict outcomes based on inputs and previous learning influences. Leabra is heavily influenced by and contributes to neural network designs and models, including emergent. == Background == It is the default algorithm in emergent (successor of PDP++) when making a new project, and is extensively used in various simulations. Hebbian learning is performed using conditional principal components analysis (CPCA) algorithm with correction factor for sparse expected activity levels. Error-driven learning is performed using GeneRec, which is a generalization of the recirculation algorithm, and approximates Almeida–Pineda recurrent backpropagation. The symmetric, midpoint version of GeneRec is used, which is equivalent to the contrastive Hebbian learning algorithm (CHL). See O'Reilly (1996; Neural Computation) for more details. The activation function is a point-neuron approximation with both discrete spiking and continuous rate-code output. Layer or unit-group level inhibition can be computed directly using a k-winners-take-all (KWTA) function, producing sparse distributed representations. A feedforward and feedback (FFFB) form of inhibition has now replaced the KWTA form of inhibition. FFFB inhibition can be efficiently implemented by using the average excitatory input and activity levels in a given layer. The net input is computed as an average, not a sum, over connections, based on normalized, sigmoidally transformed weight values, which are subject to scaling on a connection-group level to alter relative contributions. Automatic scaling is performed to compensate for differences in expected activity level in the different projections. Documentation about this algorithm can be found in the book "Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain" published by MIT press. and in the Emergent Documentation Archived 2009-04-16 at the Wayback Machine == Overview of the leabra algorithm == The pseudocode for Leabra is given here, showing exactly how the pieces of the algorithm described in more detail in the subsequent sections fit together. Iterate over minus and plus phases of settling for each event. o At start of settling, for all units: - Initialize all state variables (activation, v_m, etc.). - Apply external patterns (clamp input in minus, input & output in plus). - Compute net input scaling terms (constants, computed here so network can be dynamically altered). - Optimization: compute net input once from all static activations (e.g., hard-clamped external inputs). o During each cycle of settling, for all non-clamped units: - Compute excitatory netinput (g_e(t), aka eta_j or net) -- sender-based optimization by ignoring inactives. - Compute kWTA inhibition for each layer, based on g_i^Q: Sort units into two groups based on g_i^Q: top k and remaining k+1 -> n. If basic, find k and k+1th highest If avg-based, compute avg of 1 -> k & k+1 -> n. Set inhibitory conductance g_i from g^Q_k and g^Q_k+1 - Compute point-neuron activation combining excitatory input and inhibition o After settling, for all units, record final settling activations as either minus or plus phase (y^-_j or y^+_j). After both phases update the weights (based on linear current weight values), for all connections: o Compute error-driven weight changes with CHL with soft weight bounding o Compute Hebbian weight changes with CPCA from plus-phase activations o Compute net weight change as weighted sum of error-driven and Hebbian o Increment the weights according to net weight change. == Implementations == Emergent Archived 2015-10-03 at the Wayback Machine is the original implementation of Leabra; its most recent implementation is written in Go. It was written chiefly by Dr. O'Reilly, but professional software engineers were recently hired to improve the existing codebase. This is the fastest implementation, suitable for constructing large networks. Although emergent has a graphical user interface, it is very complex and has a steep learning curve. If you want to understand the algorithm in detail, it will be easier to read non-optimized code. For this purpose, check out the MATLAB version. There is also an R version available, that can be easily installed via install.packages("leabRa") in R and has a short introduction to how the package is used. The MATLAB and R versions are not suited for constructing very large networks, but they can be installed quickly and (with some programming background) are easy to use. Furthermore, they can also be adapted easily. == Special algorithms == Temporal differences and general dopamine modulation. Temporal differences (TD) is widely used as a model of midbrain dopaminergic firing. Primary value learned value (PVLV). PVLV simulates behavioral and neural data on Pavlovian conditioning and the midbrain dopaminergic neurons that fire in proportion to unexpected rewards (an alternative to TD). Prefrontal cortex basal ganglia working memory (PBWM). PBWM uses PVLV to train prefrontal cortex working memory updating system, based on the biology of the prefrontal cortex and basal ganglia.
Read more →
Texture compression

Texture compression is a specialized form of image compression designed for storing texture maps in 3D computer graphics rendering systems. Unlike conventional image compression algorithms, texture compression algorithms are optimized for random access. Texture compression can be applied to reduce memory usage at runtime. Texture data is often the largest source of memory usage in a mobile application. == Tradeoffs == In their seminal paper on texture compression, Beers, Agrawala and Chaddha list four features that tend to differentiate texture compression from other image compression techniques. These features are: Decoding Speed It is highly desirable to be able to render directly from the compressed texture data and so, in order not to impact rendering performance, decompression must be fast. Random Access Since predicting the order that a renderer accesses texels would be difficult, any texture compression scheme must allow fast random access to decompressed texture data. This tends to rule out many better-known image compression schemes such as JPEG or run-length encoding. Compression Rate and Visual Quality In a rendering system, lossy compression can be more tolerable than for other use cases. Some texture compression libraries, such as crunch, allow the developer to flexibly trade off compression rate vs. visual quality, using methods such as rate–distortion optimization (RDO). Encoding Speed Texture compression is more tolerant of asymmetric encoding/decoding rates as the encoding process is often done only once during the application authoring process. Given the above, most texture compression algorithms involve some form of fixed-rate lossy vector quantization of small fixed-size blocks of pixels into small fixed-size blocks of coding bits, sometimes with additional extra pre-processing and post-processing steps. Block Truncation Coding is a very simple example of this family of algorithms. Because their data access patterns are well-defined, texture decompression may be executed on-the-fly during rendering as part of the overall graphics pipeline, reducing overall bandwidth and storage needs throughout the graphics system. As well as texture maps, texture compression may also be used to encode other kinds of rendering map, including bump maps and surface normal maps. Texture compression may also be used together with other forms of map processing such as mipmaps and anisotropic filtering. == Availability == Some examples of practical texture compression systems are S3 Texture Compression (S3TC), PVRTC, Ericsson Texture Compression (ETC) and Adaptive Scalable Texture Compression (ASTC); these may be supported by special function units in modern graphics processing units (GPUs). OpenGL and OpenGL ES, as implemented on many video accelerator cards and mobile GPUs, can support multiple common kinds of texture compression - generally through the use of vendor extensions. == Supercompression == A compressed-texture can be further compressed in what is called "supercompression". Fixed-rate texture compression formats are optimized for random access and are much less efficient compared to image formats such as PNG. By adding further compression, a programmer can reduce the efficiency gap. The extra layer can be decompressed by the CPU so that the GPU receives a normal compressed texture, or in newer methods, decompressed by the GPU itself. Supercompression saves the same amount of VRAM as regular texture compression, but saves more disk space and download size. == Neural Texture Compression == Random-Access Neural Compression of Material Textures (Neural Texture Compression) is a Nvidia's technology which enables two additional levels of detail (16× more texels, so four times higher resolution) while maintaining similar storage requirements as traditional texture compression methods. The key idea is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them.
Read more →
Cerebellar model articulation controller

The cerebellar model arithmetic computer (CMAC) is a type of neural network based on a model of the mammalian cerebellum. It is also known as the cerebellar model articulation controller. It is a type of associative memory. The CMAC was first proposed as a function modeler for robotic controllers by James Albus in 1975 (hence the name), but has been extensively used in reinforcement learning and also as for automated classification in the machine learning community. The CMAC is an extension of the perceptron model. It computes a function for n {\displaystyle n} input dimensions. The input space is divided up into hyper-rectangles, each of which is associated with a memory cell. The contents of the memory cells are the weights, which are adjusted during training. Usually, more than one quantisation of input space is used, so that any point in input space is associated with a number of hyper-rectangles, and therefore with a number of memory cells. The output of a CMAC is the algebraic sum of the weights in all the memory cells activated by the input point. A change of value of the input point results in a change in the set of activated hyper-rectangles, and therefore a change in the set of memory cells participating in the CMAC output. The CMAC output is therefore stored in a distributed fashion, such that the output corresponding to any point in input space is derived from the value stored in a number of memory cells (hence the name associative memory). This provides generalisation. == Building blocks == In the adjacent image, there are two inputs to the CMAC, represented as a 2D space. Two quantising functions have been used to divide this space with two overlapping grids (one shown in heavier lines). A single input is shown near the middle, and this has activated two memory cells, corresponding to the shaded area. If another point occurs close to the one shown, it will share some of the same memory cells, providing generalisation. The CMAC is trained by presenting pairs of input points and output values, and adjusting the weights in the activated cells by a proportion of the error observed at the output. This simple training algorithm has a proof of convergence. It is normal to add a kernel function to the hyper-rectangle, so that points falling towards the edge of a hyper-rectangle have a smaller activation than those falling near the centre. One of the major problems cited in practical use of CMAC is the memory size required, which is directly related to the number of cells used. This is usually ameliorated by using a hash function, and only providing memory storage for the actual cells that are activated by inputs. == One-step convergent algorithm == Initially least mean square (LMS) method is employed to update the weights of CMAC. The convergence of using LMS for training CMAC is sensitive to the learning rate and could lead to divergence. In 2004, a recursive least squares (RLS) algorithm was introduced to train CMAC online. It does not need to tune a learning rate. Its convergence has been proved theoretically and can be guaranteed to converge in one step. The computational complexity of this RLS algorithm is O(N3). == Hardware implementation infrastructure == Based on QR decomposition, an algorithm (QRLS) has been further simplified to have an O(N) complexity. Consequently, this reduces memory usage and time cost significantly. A parallel pipeline array structure on implementing this algorithm has been introduced. Overall by utilizing QRLS algorithm, the CMAC neural network convergence can be guaranteed, and the weights of the nodes can be updated using one step of training. Its parallel pipeline array structure offers its great potential to be implemented in hardware for large-scale industry usage. == Continuous CMAC == Since the rectangular shape of CMAC receptive field functions produce discontinuous staircase function approximation, by integrating CMAC with B-splines functions, continuous CMAC offers the capability of obtaining any order of derivatives of the approximate functions. == Deep CMAC == In recent years, numerous studies have confirmed that by stacking several shallow structures into a single deep structure, the overall system could achieve better data representation, and, thus, more effectively deal with nonlinear and high complexity tasks. In 2018, a deep CMAC (DCMAC) framework was proposed and a backpropagation algorithm was derived to estimate the DCMAC parameters. Experimental results of an adaptive noise cancellation task showed that the proposed DCMAC can achieve better noise cancellation performance when compared with that from the conventional single-layer CMAC. == Summary ==
Read more →
Executive Order 14179

Executive Order 14179, titled "Removing Barriers to American Leadership in Artificial Intelligence", is an executive order signed by Donald Trump, the 47th President of the United States, on January 23, 2025. The executive order aims to initiate the process of strengthening U.S. leadership in artificial intelligence, promote AI development free from ideological bias or social agendas, establish an action plan to maintain global AI dominance, and to revise or rescind policies that conflict with these goals. == Background == === Joe Biden === This executive order comes in response to the Executive Order 14110 titled Executive Order on Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence (sometimes referred to as "Executive Order on Artificial Intelligence") signed by Joe Biden on October 30, 2023. === Donald Trump === Donald Trump rescinded Executive Order 14110 on his first day in office with the Initial Rescissions of Harmful Executive Orders and Actions executive order. On January 23, 2025, Trump signed the Removing Barriers to American Leadership in Artificial Intelligence executive order as the replacement executive order covering the development of artificial intelligence technologies. == Provisions == It revokes existing AI policies and directives that are seen as barriers to U.S. AI innovation. It mandates the creation of an action plan within 180 days to sustain U.S. AI leadership, focusing on human flourishing, economic competitiveness, and national security. It requires the review of policies, directives, and regulations related to Executive Order 14110 (from October 2023) to identify actions that may conflict with the new policy goals. Agencies are instructed to suspend, revise, or rescind actions from the previous executive order that may be inconsistent with the new policy. The Office of Management and Budget (OMB) must revise certain memoranda (M-24-10 and M-24-18) within 60 days to align with the new policy. The order specifies that it does not create new enforceable rights or benefits and should be implemented within the boundaries of existing law and appropriations. == Implementation == The NITRD program, on behalf of the Office of Science and Technology Policy (OSTP), requested public input on the development of an AI Action Plan by March 15. == Reactions == Over 10,000 public comments were submitted in response to the OSTP request for public input. OpenAI submitted comments proposing a five-point strategy focused on regulatory preemption, export controls, copyright protections, infrastructure investment, and government adoption to ensure AI innovation, promote democratic AI globally, and protect national security. They emphasized the ability to learn from copyrighted material to maintain America's lead against China's state-controlled AI efforts like DeepSeek. Google submitted comments advocating for a three-pronged plan that invests in domestic AI development through energy infrastructure reform, balanced export controls, continued research funding, and coherent federal policies, while modernizing government AI adoption and promoting innovation-friendly approaches internationally. Both OpenAI and Google urged White House opposition to foreign copyright and transparency obligations, for example in the UK Government's preferred option in their Copyright and AI consultation.
Read more →