AI Analytics Dashboard

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

  • Masking (art)

    Masking (art)

    In art, craft, and engineering, masking is the use of materials to protect areas from change, or to focus change on other areas. This can describe either the techniques and materials used to control the development of a work of art by protecting a desired area from change; or a phenomenon that (either intentionally or unintentionally) causes a sensation to be concealed from conscious attention. The term is derived from the word mask, in the sense that it hides the face from view. == In painting == Masking materials supplement a painter's dexterity and choice of applicator to control where paint is laid. Examples include the use of a stencil or masking tape to protect areas which are not to be painted. === Solid masks === Most solid masks require an adhesive to hold the mask in place while work is performed. Some, such as masking tape and frisket, come with adhesive pre-applied. Solid masks are readily available in bulk, and are used in large painting jobs. Paper products Kraft paper Butcher paper Masking tape Plastic film Frisket Polyester tape Stencils Silk screen === Liquid masks === Liquid masks are preferred where precision is needed; they prevent paint from seeping underneath, resulting in clean edges. Care must be taken to remove them without damaging the work underneath. Latex or other polymers Molten wax Gesso, typically a substrate for painting, but can also be applied to achieve masking effects == In photography == Masks used for photography are used to enhance the quality of an image. Representations of a scene—whether film, video display, or printed—do not have the dynamic contrast range available to the human eye looking directly at the same scene. Adjusting the contrast in an image helps restore some of the perceived qualities of the original scene. These adjustments are typically performed on "blown-out" highlights, and "crushed" or "muddy" shadow areas, where clipping has occurred; or on desaturated colors. Photographic masks are peculiar in that they are produced from the image they will alter, an exercise in recursion. Masks used to produce other effects are similar to those used in painting. === Controlling exposure === ==== Film ==== The basic methods of controlling exposure are dodging and burning, which respectively lighten (reduce exposure) and darken (increase exposure) areas of an image. The tools a film photographer uses range from shaped pieces of black material (such as studio foil, foam, and paper) to the photographer's hands. To create a photographic mask, a sheet of negative film is contact-exposed to the original film negative or slide positive in a particular way. Both films are then combined to produce a processed positive. The process is similar when applied using digital techniques: the inverse of the working image is reduced to an image mask; filters or other adjustments are then applied, using the mask to selectively block portions of the image. ==== Digital ==== Image editors offer at the very least a "Select All" command and a rectangular "marquee" selection tool. (The word "marquee" describes the "crawling ants" border used to highlight the active region.) Once a selection is created, further changes to the image will be confined to that area. To continue editing the rest of the image, the selection is either "deselected" or the entire image is selected. Advanced suites offer more ways to select portions of an image, as well as ways to combine these selections through. Selection masks can be switched between an editable greyscale image and a mask. They allow the user to create a mask using the suite's painting tools. === Contrast masking === When the contrast range of an image needs to be adjusted, a contrast mask is a simple solution. The processed image resembles what would be achieved when exposing through a neutral density filter, but the effects are focused highly upon the extreme regions of the image. The blocking areas of the mask coincide with the highlights of the image, and the permissive areas with the shadows, resulting in more detail appearing in each. ==== Film ==== The mask is often made from high-quality black-and-white film, such as Kodak Technical Pan, which allows for a degree of softening on the mask. Its processing time is reduced so as to not completely oppose the original negative. Both negatives are combined and registered, and collectively exposed with additional time to compensate for the presence of the mask. ==== Digital ==== Contrast masking is made simpler with digital editing. A grayscale version of the image is produced, either by desaturation or by calculating selected ratios of the image's color channels, inverted, and blurred. The mask and original image are blended together to produce the final processed image. Some image editors allow for refinement of the effect by changing the strength of the blend. Contrast masking can be considered to be the opposite of gamma correction, which adjusts the midtones of an image. Effects similar to contrast masking can be achieved by adjusting the response curves of an image. === Unsharp masking === A derivative of contrast masking is unsharp masking, an unusual term for a process intended to increase the apparent sharpness (acutance) of an image. Unsharp masking uses a blurred form of the image to increase contrast along regions of moderate contrast difference. Around edges, the blur region causes highlights to overexpose and shadows to underexpose. Taken to an extreme, the edges become overly visible and detract from the quality of the image—this is referred to as halation. Unsharp masking does not increase the actual sharpness, as it cannot recover details lost to blurring. ==== Film ==== Unsharp masking allows the photographer to sharpen areas that have become blurred in the original negative, due to long shutter speed/exposure time, or from using a wide aperture/"fast" lens. When creating the unsharp mask, extra space or diffusing material is added between the image and the mask to produce the necessary blur. ==== Digital ==== Unsharp masking has become automated in digital editing, with higher-end suites offering the process as a "tool" or "filter" in their standard sharpening kits—the actual creation of a mask is bypassed in favor of calculations that represent the mask's effect. The process depends on three factors: the radius of the blur, the strength of the effect, and the threshold degree of contrast above which the effect will be applied. (Adjusting the threshold allows the editor to apply the effect selectively upon moderately defined edges and ignore image noise.) Unsharp masking is computationally more complex than other sharpening algorithms, but results in a higher-quality remedy. Deconvolution allows for truer sharpening, but is much more complex than unsharp masking.

    Read more →
  • Argumentation theory

    Argumentation theory

    Argumentation theory is the interdisciplinary study of how conclusions can be supported or undermined by premises through logical reasoning. With historical origins in logic, dialectic, and rhetoric, argumentation theory includes the arts and sciences of civil debate, dialogue, conversation, and persuasion. It studies rules of inference, logic, and procedural rules in both artificial and real-world settings. Argumentation includes various forms of dialogue such as deliberation and negotiation which are concerned with collaborative decision-making procedures. It also encompasses eristic dialogue, the branch of social debate in which victory over an opponent is the primary goal, and didactic dialogue used for teaching. This discipline also studies the means by which people can express and rationally resolve or at least manage their disagreements. Argumentation is a daily occurrence, such as in public debate, science, and law. For example in law, in courts by the judge, the parties and the prosecutor, in presenting and testing the validity of evidences. Also, argumentation scholars study the post hoc rationalizations by which organizational actors try to justify decisions they have made irrationally. Argumentation is one of four rhetorical modes (also known as modes of discourse), along with exposition, description, and narration. == Key components of argumentation == Some key components of argumentation are: Understanding and identifying arguments, either explicit or implied, and the goals of the participants in the different types of dialogue. Identifying the premises from which conclusions are derived. Establishing the "burden of proof" – determining who made the initial claim and is thus responsible for providing evidence why their position merits acceptance. For the one carrying the "burden of proof", the advocate, to marshal evidence for their position in order to convince or force the opponent's acceptance. The method by which this is accomplished is producing valid, sound, and cogent arguments, devoid of weaknesses, and not easily attacked. In a debate, fulfillment of the burden of proof creates a burden of rejoinder. One must try to identify faulty reasoning in the opponent's argument, to attack the reasons/premises of the argument, to provide counterexamples if possible, to identify any fallacies, and to show why a valid conclusion cannot be derived from the reasons provided for their argument. For example, consider the following exchange, illustrating the No true Scotsman fallacy: Argument: "No Scotsman puts sugar on his porridge." Reply: "But my friend Angus, who is a Scotsman, likes sugar with his porridge." Rebuttal: "Well perhaps, but no true Scotsman puts sugar on his porridge." In this dialogue, the proposer first offers a premise, the premise is challenged by the interlocutor, and so the proposer offers a modification of the premise, which is designed only to evade the challenge provided. == Internal structure of arguments == Typically an argument has an internal structure, comprising the following: a set of assumptions or premises, a method of reasoning or deduction, and a conclusion or point. An argument has one or more premises and one conclusion. Often classical logic is used as the method of reasoning so that the conclusion follows logically from the assumptions or support. One challenge is that if the set of assumptions is inconsistent then anything can follow logically from inconsistency. Therefore, it is common to insist that the set of assumptions be consistent. It is also good practice to require the set of assumptions to be the minimal set, with respect to set inclusion, necessary to infer the consequent. Such arguments are called MINCON arguments, short for minimal consistent. Such argumentation has been applied to the fields of law and medicine. A non-classical approach to argumentation investigates abstract arguments, where 'argument' is considered a primitive term, so no internal structure of arguments is taken into account. == Types of dialogue == In its most common form, argumentation involves an individual and an interlocutor or opponent engaged in dialogue, each contending differing positions and trying to persuade each other, but there are various types of dialogue: Persuasion dialogue aims to resolve conflicting points of view of different positions. Negotiation aims to resolve conflicts of interests by cooperation and dealmaking. Inquiry aims to resolve general ignorance by the growth of knowledge. Deliberation aims to resolve a need to take action by reaching a decision. Information seeking aims to reduce one party's ignorance by requesting information from another party that is in a position to know something. Eristic aims to resolve a situation of antagonism through verbal fighting. == Argumentation and the grounds of knowledge == Argumentation theory had its origins in foundationalism, a theory of knowledge (epistemology) in the field of philosophy. It sought to find the grounds for claims in the forms (logic) and materials (factual laws) of a universal system of knowledge. The dialectical method was made famous by Plato and his use of Socrates critically questioning various characters and historical figures. But argument scholars gradually rejected Aristotle's systematic philosophy and the idealism in Plato and Kant. They questioned and ultimately discarded the idea that argument premises take their soundness from formal philosophical systems. The field thus broadened. One of the original contributors to this trend was the philosopher Chaïm Perelman, who together with Lucie Olbrechts-Tyteca introduced the French term la nouvelle rhetorique in 1958 to describe an approach to argument which is not reduced to application of formal rules of inference. Perelman's view of argumentation is much closer to a juridical one, in which rules for presenting evidence and rebuttals play an important role. Karl R. Wallace's seminal essay, "The Substance of Rhetoric: Good Reasons" in the Quarterly Journal of Speech (1963) 44, led many scholars to study "marketplace argumentation" – the ordinary arguments of ordinary people. The seminal essay on marketplace argumentation is Ray Lynn Anderson's and C. David Mortensen's "Logic and Marketplace Argumentation" Quarterly Journal of Speech 53 (1967): 143–150. This line of thinking led to a natural alliance with late developments in the sociology of knowledge. Some scholars drew connections with recent developments in philosophy, namely the pragmatism of John Dewey and Richard Rorty. Rorty has called this shift in emphasis "the linguistic turn". In this new hybrid approach argumentation is used with or without empirical evidence to establish convincing conclusions about issues which are moral, scientific, epistemic, or of a nature in which science alone cannot answer. Out of pragmatism and many intellectual developments in the humanities and social sciences, "non-philosophical" argumentation theories grew which located the formal and material grounds of arguments in particular intellectual fields. These theories include informal logic, social epistemology, ethnomethodology, speech acts, the sociology of knowledge, the sociology of science, and social psychology. These new theories are not non-logical or anti-logical. They find logical coherence in most communities of discourse. These theories are thus often labeled "sociological" in that they focus on the social grounds of knowledge. == Kinds of argumentation == === Conversational argumentation === The study of naturally occurring conversation arose from the field of sociolinguistics. It is usually called conversation analysis (CA). Inspired by ethnomethodology, it was developed in the late 1960s and early 1970s principally by the sociologist Harvey Sacks and, among others, his close associates Emanuel Schegloff and Gail Jefferson. Sacks died early in his career, but his work was championed by others in his field, and CA has now become an established force in sociology, anthropology, linguistics, speech-communication and psychology. It is particularly influential in interactional sociolinguistics, discourse analysis and discursive psychology, as well as being a coherent discipline in its own right. Recently CA techniques of sequential analysis have been employed by phoneticians to explore the fine phonetic details of speech. Empirical studies and theoretical formulations by Sally Jackson and Scott Jacobs, and several generations of their students, have described argumentation as a form of managing conversational disagreement within communication contexts and systems that naturally prefer agreement. === Mathematical argumentation === The basis of mathematical truth has been the subject of long debate. Frege in particular sought to demonstrate (see Gottlob Frege, The Foundations of Arithmetic, 1884, and Begriffsschrift, 1879) that arithmetical truths can be derived from purely logical axioms and therefore are, in th

    Read more →
  • Akoma Ntoso

    Akoma Ntoso

    Akoma Ntoso (Architecture for Knowledge-Oriented Management of African Normative Texts using Open Standards and Ontologies, AKN) is an international technical standard for representing legal documents (executive, legislative, and judiciary) in a structured manner using a domain specific, legal XML vocabulary. The term akoma ntoso means "linked hearts" in the Akan language of West Africa. Akoma Ntoso is a legal document standard designed to serve as a basis for modern machine-readable and fully digital legislative and judicial processes. This is achieved by providing a coherent syntax and well-defined semantics to represent legal documents in a digital format. It is designed to be suitable as a common exchange format in all parliamentary, legal and judicial systems around the world. Taking advantage of the shared heritage present in all legal systems, Akoma Ntoso has been developed to have ample flexibility to respond to all the differences in texts, languages, and legal practices. Aiming to expand on certain common practices, the standard therefore has a broad scope. It includes a common extensible model for data (the document content) and metadata (such as bibliographic information and annotations). Specifically, as a common legal document standard for the interchange of legal documents it is designed to be highly flexible in its support of documents and functionalities, maintaining a large set of both structural and semantic building blocks (over 500 entities in version 3.0) for representing this wide variety of document types of virtually all legal traditions. It is extensible in order to allow for modifications to address the individual criteria of organizations or unique aspects of various legal practices and languages without sacrificing interoperability with other systems. Akoma Ntoso is as such part of a wider approach to developing open, non-proprietary technical standards for structuring legal documents and information under the name of Legal XML, which also includes formats and standards for, e.g., eContracts, eNotarization, electronic court filings, the technical representation of legal norms and rules (LegalRuleML) or technical standards for the interfaces of, e.g., litigant portal exchange platforms. Akoma Ntoso allows machine-driven processes to operate on the syntactic and semantic components of digital parliamentary, judicial and legislative documents, thus facilitating the development of high-quality information resources. It can substantially enhance the performance, accountability, quality and openness of parliamentary and legislative operations based on best practices and guidance through machine-assisted drafting and machine-assisted (legal) analysis. Embedded in the environment of the semantic web, it forms the basis for a heterogenous yet interoperable ecosystem, with which these tools can operate and communicate, as well as for future applications and use cases based on digital law or rule representation. == Definition == The Akoma Ntoso standard defines a set of machine readable electronic representations in XML format of the building blocks of parliamentary, legislative and judiciary documents. As official self-description, the standard (...) defines a set of simple, technology-neutral electronic representations of parliamentary, legislative and judiciary documents for e-services in a worldwide context and provides an enabling framework for the effective exchange of "machine readable" parliamentary, legislative and judiciary documents such as legislation, debate record, minutes, judgements, etc. Providing access to primary legal materials, parliamentary works and judiciaries documents is not just a matter of giving physical or on-line access to them. "Open access" requires the information to be described and classified in a uniform and organized way so that content is structured into meaningful elements that can be read and understood by software applications, so that the content is made "machine readable" and more sophisticated applications than on-screen display are made possible. The standard is composed of: an XML vocabulary that defines the mapping between the structure of legal documents and their equivalent in XML; specifications of an XML schema that defines the structure of legal documents in XML. They provide rich possibilities of description for several types of parliamentary, legislative and judiciary document, such as bills, acts and parliamentary records, judgments, or gazettes; a recommended naming convention for providing unique identifiers to legal sources based on FRBR model; a MIME type definition. == History and adoption == Akoma Ntoso started as an UNDESA project in 2004 within the initiative "Strengthening Parliaments' Information Systems in Africa". Its core vocabulary was created mostly by Monica Palmirani and Fabio Vitali, two professors from the Centre for Research in the History, Philosophy, and Sociology of Law and in Computer Science and Law (CIRSFID) of the University of Bologna. A first legislative text editor supporting Akoma Ntoso was developed in 2007 on the base of OpenOffice. In 2010 European Parliament developed an open source web-based application called AT4AM based on Akoma Ntoso for facilitating the production and the management of legislative amendments. Thanks to this project, the application of Akoma Ntoso could be extended to new type of documents (e.g. legislative proposal, transcript) and to other scenarios (e.g., multilingual translation process). Akoma Ntoso also was explicitly designed to be compliant with CEN Metalex, one of the other popular legal standards, which is used in the legislation.gov.uk. In 2012, the Akoma Ntoso specifications became the main working base for the activities of the LegalDocML Technical Committee within the LegalXML member section of OASIS. The "United States Legislative Markup" (USLM) schema for the United States Code (the US codified laws), developed in 2013, and the LexML Brasil XML schema for Brazilian legislative and judiciary documents, developed before, in 2008, were both designed to be consistent with Akoma Ntoso. The United States Library of Congress created the Markup of US Legislation in Akoma Ntoso challenge in July 2013 to create representations of selected US bills using the most recent Akoma Ntoso standard within a couple months for a $5000 prize, and the Legislative XML Data Mapping challenge in September 2013 to produce a data map for US bill XML and UK bill XML to the most recent Akoma Ntoso schema within a couple months for a $10000 prize. The National Archives of UK converted all the legislation in AKN in 2014. The availability of bulk legislation "moved the UK's ranking from fourth to first, in the 2014 Global Open Data Index, for legislation". The Senate of Italian Republic provides, since July 2016, all the bills in Akoma Ntoso as bulk in open data repository. The German Federal Ministry of the Interior started the project Elektronische Gesetzgebung ("Electronic Legislation") in 2015/2016 and published Version 1.0 of the German application profile "LegalDocML.de" in March 2020. The projects aim is to digitalize the entire legislative lifecycle from drafting to publication. Germany decided to adopt a model-driven development approach to creating and providing a subschema-based application profile in order to ensure interoperability among organizationally independent actors, each with their respective IT landscapes and tools. In this initial version LegalDocML.de covers draft bills in the form of laws, regulations and general administrative directives. As part of an ongoing development process, the standard could incrementally be expanded in future stages to include all relevant document types of parliamentary, legislative and promulgation processes and tools. The High-Level Committee on Management (HLCM), part of the United Nations System Chief Executives Board for Coordination, set up a Working Group on Document Standards that approved in April 2017 to adopt Akoma Ntoso as standard for modeling its documentation. Akoma Ntoso in its version 1.0 is finally adopted as OASIS standard in the frame of LegalDocML in August 2018.

    Read more →
  • Whisper (speech recognition system)

    Whisper (speech recognition system)

    Whisper is a machine learning model for speech recognition and transcription, created by OpenAI and first released as open-source software in September 2022. It is capable of transcribing speech in English and multiple other languages, and can translate several non-English languages into English. Whisper is a weakly-supervised deep learning acoustic model, made using an encoder-decoder transformer architecture. OpenAI claims that the combination of different training data and post-training filtering used in its development has led to improved recognition of accents, background noise, and jargon compared to previous approaches. While the model does not outperform larger, more specialized models and still experiences AI hallucination, it has been showed to be useful for general sound recognition and has many applications across different industries. == Background == Speech recognition has had a long history in research; the first approaches made use of statistical methods, such as dynamic time warping, and later hidden Markov models. At around the 2010s, deep neural network approaches became more common for speech recognition models, which were enabled by the availability of large datasets ("big data") and increased computational performance. Early approaches to deep learning in speech recognition included convolutional neural networks, which were limited due to their inability to capture sequential data, which later led to developments of Seq2seq approaches, which include recurrent neural networks, which made use of long short-term memory. Transformers, introduced in 2017 by Google, displaced many prior state-of-the-art approaches across a wide range in machine learning, and started becoming the core neural architecture in fields such as language modeling and computer vision. Weakly-supervised approaches to training acoustic models were recognized in the early 2020s as promising for speech recognition approaches using deep neural networks. According to a NYT report, in 2021 OpenAI believed they exhausted sources of higher-quality data to train their large language models and decided to complement scraped web text with transcriptions of YouTube videos and podcasts, and developed Whisper to solve this task. Whisper Large V2 was released on December 8, 2022, followed by Whisper Large V3 being released in November 2023, during the OpenAI Dev Day. In March 2025, OpenAI released new transcription models based on GPT-4o and GPT-4o mini, both of which have lower error rates than Whisper. == Architecture == The Whisper architecture is based on an encoder-decoder transformer. Input audio is resampled to 16,000 Hertz (Hz) and converted to an 80-channel Log-magnitude Mel spectrogram using 25 ms windows with a 10 ms stride. The spectrogram is then normalized to a [-1, 1] range with near-zero mean. The encoder takes this Mel spectrogram as input and processes it. It first passes through two convolutional layers. Sinusoidal positional embeddings are added. It is then processed by a series of Transformer encoder blocks (with pre-activation residual connections). The encoder's output is layer normalized. The decoder is a standard transformer decoder. It has the same width and Transformer blocks as the encoder. It uses learned positional embeddings and tied input-output token representations (using the same weight matrix for both the input and output embeddings). It uses a byte-pair encoding tokenizer, of the same kind as used in GPT-2. English-only models use the GPT-2 vocabulary, while multilingual models employ a re-trained multilingual vocabulary with the same number of words. Special tokens are used to allow the decoder to perform multiple tasks: Tokens that denote language (one unique token per language). Tokens that specify task (<|transcribe|> or <|translate|>). Tokens that specify if no timestamps are present (<|notimestamps|>). If the token is not present, then the decoder predicts timestamps relative to the segment, and quantized to 20 ms intervals. <|nospeech|> for voice activity detection. <|startoftranscript|>, and <|endoftranscript|> . Any text that appears before <|startoftranscript|> is not generated by the decoder, but given to the decoder as context. Loss is only computed over non-contextual parts of the sequence, i.e. tokens between these two special tokens. == Training data == The training dataset consists of 680,000 hours of labeled audio-transcript pairs sourced from the internet using semi-supervised learning. This includes 117,000 hours in 96 non-English languages and 125,000 hours of X→English translation data, where X stands for any non-English language. Preprocessing involved standardization of transcripts, filtering to remove machine-generated transcripts using heuristics (e.g., punctuation, capitalization), language identification and matching with transcripts, fuzzy deduplication, and deduplication with evaluation datasets to avoid data contamination. Speechless segments were also included to allow voice activity detection training. For the files still remaining after the filtering process, audio files were then broken into 30-second segments paired with the subset of the transcript that occurs within that time. If this predicted spoken language differed from the language of the text transcript associated with the audio, that audio-transcript pair was not used for training the speech recognition models, but instead for training translation. The model was trained using the AdamW optimizer with gradient norm clipping and a linear learning rate decay with warmup, with batch size 256 segments. Training proceeded for 1 million updates (approximately 2-3 epochs). No data augmentation or regularization, except for the Large V2 model, which used SpecAugment, Stochastic Depth, and BPE Dropout. The training used data parallelism with float16, dynamic loss scaling, and activation checkpointing. === Post-training filtering === After training the first model, researchers ran it on different subsets of the training data, each representing a distinct source. Data sources were ranked by a combination of their error rate and size. Manual inspection of the top-ranked sources (high error, large size) helped determine if the source was low quality (e.g., partial transcriptions, inaccurate alignment). After training, it was fine-tuned to suppress the prediction of speaker names and low-quality sources were then removed. == Capacity == While Whisper does not outperform models which specialize in the LibriSpeech dataset, when tested across many datasets, it is more robust and makes 55.2% fewer errors than other models. Whisper has a differing error rate with respect to transcribing different languages, with a higher word error rate in languages not well-represented in the training data. The authors found that multi-task learning improved overall performance compared to models specialized to one task. They conjectured that the best Whisper model trained is still underfitting the dataset, and larger models and longer training can result in better models. Third-party evaluations have found varying levels of AI hallucination. A study of transcripts of public meetings found hallucinations in eight out of every 10 transcripts, while an engineer discovered hallucinations in "about half" of 100 hours of transcriptions and a developer identified them in "nearly every one" of 26,000 transcripts. A study of 13,140 short audio segments (averaging 10 seconds) found 187 hallucinations (1.4%), 38% of which generated text that could be harmful because it inserted false references to things like race, non-existent medications, or violent events that were not in the audio. == Applications == The model has been used as the base for many applications, such as a unified model for speech recognition and more general sound recognition. Whisper has also been integrated into the workflow of biomedical research. In 2025, a study on Alzheimer's disease detection used the model to transcribe spontaneous speech recordings. The transcripts that were generated by the model were combined with LLM vector embeddings and traditional classifiers to help classify the patients' health. Another application is when OVALYTICS incorporated Whisper to transcribe YouTube videos and automate content moderation systems, which improved its detection of offensive content. The model has also been used in academic libraries and cultral heritage institutions to generate transcripts and captions for their digitized audiovisual collections. In a 2025 case study, Emory University Libraries found that Whisper reduced the labor used in transcription by around 30-35%, shifting work from text creation to text correction. However, human review is still necessary to make sure accuracy, formatting, and accessibility are all standard.

    Read more →
  • Language resource

    Language resource

    In linguistics and language technology, a language resource is a "[composition] of linguistic material used in the construction, improvement and/or evaluation of language processing applications, (...) in language and language-mediated research studies and applications." According to Bird & Simons (2003), this includes data, i.e. "any information that documents or describes a language, such as a published monograph, a computer data file, or even a shoebox full of handwritten index cards. The information could range in content from unanalyzed sound recordings to fully transcribed and annotated texts to a complete descriptive grammar", tools, i.e., "computational resources that facilitate creating, viewing, querying, or otherwise using language data", and advice, i.e., "any information about what data sources are reliable, what tools are appropriate in a given situation, what practices to follow when creating new data". The latter aspect is usually referred to as "best practices" or "(community) standards". In a narrower sense, language resource is specifically applied to resources that are available in digital form, and then, "encompassing (a) data sets (textual, multimodal/multimedia and lexical data, grammars, language models, etc.) in machine readable form, and (b) tools/technologies/services used for their processing and management". == Typology == As of May 2020, no widely used standard typology of language resources has been established (current proposals include the LREMap, METASHARE, and, for data, the LLOD classification). Important classes of language resources include data lexical resources, e.g., machine-readable dictionaries, linguistic corpora, i.e., digital collections of natural language data, linguistic data bases such as the Cross-Linguistic Linked Data collection, tools linguistic annotations and tools for creating such annotations in a manual or semiautomated fashion (e.g., tools for annotating interlinear glossed text such as Toolbox and FLEx, or other language documentation tools), applications for search and retrieval over such data (corpus management systems), for automated annotation (part-of-speech tagging, syntactic parsing, semantic parsing, etc.), metadata and vocabularies vocabularies, repositories of linguistic terminology and language metadata, e.g., MetaShare (for language resource metadata), the ISO 12620 data category registry (for linguistic features, data structures and annotations within a language resource), or the Glottolog database (identifiers for language varieties and bibliographical database). == Language resource publication, dissemination and creation == A major concern of the language resource community has been to develop infrastructures and platforms to present, discuss and disseminate language resources. Selected contributions in this regard include: a series of International Conferences on Language Resources and Evaluation (LREC), the European Language Resources Association (ELRA, EU-based), and the Linguistic Data Consortium (LDC, US-based), which represent commercial hosting and dissemination platforms for language resources, the Open Languages Archives Community (OLAC), which provides and aggregates language resource metadata, the Language Resources and Evaluation Journal (LREJ), the European Language Grid is a European platform for language technologies (eg services), data and resources. As for the development of standards and best practices for language resources, these are subject of several community groups and standardization efforts, including ISO Technical Committee 37: Terminology and other language and content resources (ISO/TC 37), developing standards for all aspects of language resources, W3C Community Group Best Practices for Multilingual Linked Open Data (BPMLOD), working on best practice recommendations for publishing language resources as Linked Data or in RDF, W3C Community Group Linked Data for Language Technology (LD4LT), working on linguistic annotations on the web and language resource metadata, W3C Community Group Ontology-Lexica (OntoLex), working on lexical resources, the Open Linguistics working group of the Open Knowledge Foundation, working on conventions for publishing and linking open language resources, developing the Linguistic Linked Open Data cloud, the Text Encoding Initiative (TEI), working on XML-based specifications for language resources and digitally edited text.

    Read more →
  • Blackboard system

    Blackboard system

    A blackboard system is an artificial intelligence approach based on the blackboard architectural model, where a common knowledge base, the "blackboard", is iteratively updated by a diverse group of specialist knowledge sources, starting with a problem specification and ending with a solution. Each knowledge source updates the blackboard with a partial solution when its internal constraints match the blackboard state. In this way, the specialists work together to solve the problem. The blackboard model was originally designed as a way to handle complex, ill-defined problems, where the solution is the sum of its parts. == Metaphor == The following scenario provides a simple metaphor that gives some insight into how a blackboard functions: A group of specialists are seated in a room with a large blackboard. They work as a team to brainstorm a solution to a problem, using the blackboard as the workplace for cooperatively developing the solution. The session begins when the problem specifications are written onto the blackboard. The specialists all watch the blackboard, looking for an opportunity to apply their expertise to the developing solution. When someone writes something on the blackboard that allows another specialist to apply their expertise, the second specialist records their contribution on the blackboard, hopefully enabling other specialists to then apply their expertise. This process of adding contributions to the blackboard continues until the problem has been solved. == Components == A blackboard-system application consists of three major components The software specialist modules, which are called knowledge sources (KSs). Like the human experts at a blackboard, each knowledge source provides specific expertise needed by the application. The blackboard, a shared repository of problems, partial solutions, suggestions, and contributed information. The blackboard can be thought of as a dynamic "library" of contributions to the current problem that have been recently "published" by other knowledge sources. The control shell, which controls the flow of problem-solving activity in the system. Just as the eager human specialists need a moderator to prevent them from trampling each other in a mad dash to grab the chalk, KSs need a mechanism to organize their use in the most effective and coherent fashion. In a blackboard system, this is provided by the control shell. === Learnable Task Modeling Language === A blackboard system is the central space in a multi-agent system. It's used for describing the world as a communication platform for agents. To realize a blackboard in a computer program, a machine readable notation is needed in which facts can be stored. One attempt in doing so is a SQL database, another option is the Learnable Task Modeling Language (LTML). The syntax of the LTML planning language is similar to PDDL, but adds extra features like control structures and OWL-S models. LTML was developed in 2007 as part of a much larger project called POIROT (Plan Order Induction by Reasoning from One Trial), which is a Learning from demonstrations framework for process mining. In POIROT, Plan traces and hypotheses are stored in the LTML syntax for creating semantic web services. Here is a small example: A human user is executing a workflow in a computer game. The user presses some buttons and interacts with the game engine. While the user interacts with the game, a plan trace is created. That means the user's actions are stored in a logfile. The logfile gets transformed into a machine readable notation which is enriched by semantic attributes. The result is a textfile in the LTML syntax which is put on the blackboard. Agents (software programs in the blackboard system) are able to parse the LTML syntax. == Implementations == We start by discussing two well known early blackboard systems, BB1 and GBB, below and then discuss more recent implementations and applications. The BB1 blackboard architecture was originally inspired by studies of how humans plan to perform multiple tasks in a trip, used task-planning as a simplified example of tactical planning for the Office of Naval Research. Hayes-Roth & Hayes-Roth found that human planning was more closely modeled as an opportunistic process, in contrast to the primarily top-down planners used at the time: While not incompatible with successive-refinement models, our view of planning is somewhat different. We share the assumption that planning processes operate in a two-dimensional planning space defined on time and abstraction dimensions. However, we assume that people's planning activity is largely opportunistic. That is, at each point in the process, the planner's current decisions and observations suggest various opportunities for plan development. The planner's subsequent decisions follow up on selected opportunities. Sometimes, these decision-sequences follow an orderly path and produce a neat top-down expansion as described above. However, some decisions and observations might also suggest less orderly opportunities for plan development. A key innovation of BB1 was that it applied this opportunistic planning model to its own control, using the same blackboard model of incremental, opportunistic, problem-solving that was applied to solve domain problems. Meta-level reasoning with control knowledge sources could then monitor whether planning and problem-solving were proceeding as expected or stalled. If stalled, BB1 could switch from one strategy to another as conditions – such as the goals being considered or the time remaining – changed. BB1 was applied in multiple domains: construction site planning, inferring 3-D protein structures from X-ray crystallography, intelligent tutoring systems, and real-time patient monitoring. BB1 also allowed domain-general language frameworks to be designed for wide classes of problems. For example, the ACCORD language framework defined a particular approach to solving configuration problems. The problem-solving approach was to incrementally assemble a solution by adding objects and constraints, one at a time. Actions in the ACCORD language framework appear as short English-like commands or sentences for specifying preferred actions, events to trigger KSes, preconditions to run a KS action, and obviation conditions to discard a KS action that is no longer relevant. GBB focused on efficiency, in contrast to BB1, which focused more on sophisticated reasoning and opportunistic planning. GBB improves efficiency by allowing blackboards to be multi-dimensional, where dimensions can be either ordered or not, and then by increasing the efficiency of pattern matching. GBB1, one of GBB's control shells implements BB1's style of control while adding efficiency improvements. Other well-known of early academic blackboard systems are the Hearsay II speech recognition system and Douglas Hofstadter's Copycat and Numbo projects. Some more recent examples of deployed real-world applications include: The PLAN component of the Mission Control System for RADARSAT-1, an Earth observation satellite developed by Canada to monitor environmental changes and Earth's natural resources. The GTXImage CAD software by GTX Corporation was developed in the early 1990s using a set of rulebases and neural networks as specialists operating on a blackboard system. Adobe Acrobat Capture (now discontinued), as it used a blackboard system to decompose and recognize image pages to understand the objects, text, and fonts on the page. This function is currently built into the retail version of Adobe Acrobat as "OCR Text Recognition". Details of a similar OCR blackboard for Farsi text are in the public domain. Blackboard systems are used routinely in many military C4ISTAR systems for detecting and tracking objects. Another example of current use is in Game AI, where they are considered a standard AI tool to help with adding AI to video games. == Recent developments == Blackboard-like systems have been constructed within modern Bayesian machine learning settings, using agents to add and remove Bayesian network nodes. In these 'Bayesian Blackboard' systems, the heuristics can acquire more rigorous probabilistic meanings as proposal and acceptances in Metropolis Hastings sampling though the space of possible structures. Conversely, using these mappings, existing Metropolis-Hastings samplers over structural spaces may now thus be viewed as forms of blackboard systems even when not named as such by the authors. Such samplers are commonly found in musical transcription algorithms for example. Blackboard systems have also been used to build large-scale intelligent systems for the annotation of media content, automating parts of traditional social science research. In this domain, the problem of integrating various AI algorithms into a single intelligent system arises spontaneously, with blackboards providing a way for a collection of distributed, modular natural language processing algorithm

    Read more →
  • Roborace

    Roborace

    Roborace was a competition with autonomously driving, electrically powered vehicles. Founded in 2015 by Denis Sverdlov, it aimed to be the first global championship for autonomous cars. From 2017 to 2019, the official CEO was 2016–17 Formula E champion, Lucas Di Grassi, who later became a member of Roborace’s supervisory board. The series tested their technology and race formats at FIA Formula E Championship events during 2016–2018. In 2019 Roborace organized Season Alpha, which consisted of 4 trial racing events with several independent teams competing against each other for the first time. In 2020–21 Roborace held Season Beta with 7 competing teams. All teams utilized the same chassis and powertrain, but they had to develop their own real-time computing algorithms and artificial intelligence technologies. In May 2022, Arrival, the owner of Roborace, confirmed that they were no longer continuing the Roborace programme, but that they were hoping to find alternative funding. In February 2024, after getting its stock delisted from the Nasdaq, Arrival's UK division entered administration, with future plans of a sale of Arrival and all of its affiliated assets. == Cars == === Robocar === The world's first purpose-built autonomous racing car, Robocar, was designed by Daniel Simon, who previously worked on vehicles for movies such as Tron: Legacy and Oblivion, as well as designing the livery for the 2011 HRT Formula One car. Michelin is the official tyre supplier, and the internal computing processors (Drive PX 2) are Nvidia. The chassis itself is shaped like a teardrop, improving aerodynamic efficiency. The car weighs around 1350 kg and is 4.8 metres (16 ft) long and 2 metres (6.6 ft) wide. It has four electric motors, each with a power of 135 kW producing over 500 hp combined, and utilizes a 840V battery. For navigation, it relies on a mixture of optical systems, radars, lidars and ultrasonic sensors. The vehicle has been demonstrated at speeds of almost 300 km/h (190 mph). === DevBot === Development of the Robocar started in early 2016, with a first outing of a test vehicle, the so-called DevBot, following in the summer of the same year. The test car consisted of the same internal units (battery, motor, electronics) used in the Robocar, but were placed in the chassis of a Ginetta LMP3 car without an engine cover in order to provide better cooling and access. DevBot saw its first public outing at the Formula E pre-season tests in Donington Park in August 2016. After battery issues in Hong Kong caused the development team to abandon their demonstration run, the DevBot successfully drove twelve laps around the Moulay El Hassan Formula E circuit in Marrakesh. Other test tracks included Michelin's testing ground in Ladoux and the Silverstone Stowe Circuit. During testing ahead of the 2017 Buenos Aires ePrix, two DevBot cars raced against each other autonomously, resulting in one of the vehicles crashing on a corner. During the 2017–18 Formula E season, Roborace pitched pro-drifter Ryan Tuerck against a DevBot at the Rome ePrix. At the Berlin ePrix, Roborace held the Human + Machine Challenge, the first race for combined teams of human drivers and AIs using a pair of Devbots. === DevBot 2.0 === An upgraded version of DevBot was announced in late 2018, and after private testing made its public debut in 2019 at the inaugural Season Alpha event. DevBot 2.0 uses the same technology as both Robocar and DevBot, with the main changes being a conversion to being driven on the rear axle only, a lower position for the driver for safety reasons and a bespoke composite bodywork. == Seasons == === Testing === ==== 2016–17 Formula E season ==== Roborace appeared at a number of Formula E events during the 2016–17 Formula E season. However, in this period only test drives with two different DevBots took place. Within the framework of the 2017 Buenos Aires ePrix both DevBot vehicles drove against each other on a race track for the first time. There were also DevBot demonstrations at the 2016 Marrakesh ePrix, 2017 Berlin ePrix, 2017 New York City ePrix and 2017 Montreal ePrix. At the 2017 Paris ePrix, the developers also let a Robocar onto the track for the first time, even though the vehicle only drove the track at walking speed. ==== 2017–18 Formula E season ==== At the start of the 2017/18 Formula E season, the Roborace developers once again tested the DevBot during a public time trial between the Roborace CI and the TV presenter Nicki Shields at the 2017 Hong Kong ePrix. As part of a similar time trial at the 2018 Rome ePrix, drift professional Ryan Tuerck also tested the DevBot. The Human + Machine Challenge was created for the Formula E race on the Berlin ePrix. A team of doctoral students from the Technical University of Munich (TUM) and the University of Pisa programmed the software for the Devbot to drive autonomously around the circuit in Berlin. Afterwards both teams in combination with a human driver competed in a public time trial. The vehicle of the team of the Technical University of Munich finished the Human + Machine Challenge with an average lap time of 91.59 seconds, almost four seconds faster than that of the University of Pisa with 95.36 seconds and thus won the Challenge. At the Goodwood Festival of Speed, Robocar became the first ever fully autonomous race car to complete the Goodwood Hill Climb. The vehicle completed the first official autonomous run on 13 July 2018 within the framework of the event. === Season Alpha (2019) === Season Alpha took place at various locations in Europe and North America with the aim of testing several competition formats using the new DevBot 2.0. The first event was held at the Circuito Monteblanco in Spain, and featured the first race between two fully autonomous cars. The events were not broadcast live, instead short clips on YouTube were released. Two teams were competing: Arrival and the Technical University of Munich. On 7 July 2019, the Roborace DevBot 2.0 car set the first ever autonomous official timed run at Goodwood Festival of Speed, with a time of 66.96 s and a top speed of 162.8 km/h (101.2 mph). This is currently the record for autonomous vehicles. Roborace also set the Guinness World Record for having the fastest autonomous car in the world. The Robocar reached a speed of 282.42 km/h (175.49 mph). === Season Beta (2020–21) === The second testing season took place at various locations between September 2020 and October 2021, featuring 16 races and involving mixed reality elements dubbed "Roborace Metaverse", which is based on Roborace's patented technology. The program of Season Beta competitions has gradually complicating rules arranged in a progression of so-called missions. Each mission consists of two racing rounds — one round per day. A mission plan issued by Roborace for each mission defines its objectives, rules, and point-scoring system. The key objective of Season Beta is to come to the point when the majority of competing teams have developed sufficient capability for wheel-to-wheel racing in Season 1. There were 7 teams competing in Season Beta: Arrival Racing (UK/Russia), Autonomous Racing Graz (Austria), MIT Driverless (United States), Acronis SIT (Switzerland), University of Pisa (Italy), PoliMOVE (Italy), CMU (United States).

    Read more →
  • Evolutionary computation

    Evolutionary computation

    Evolutionary computation (EC) from computer science is a family of algorithms for global optimization inspired by biological evolution, and a subfield of computational intelligence and soft computing studying these algorithms. In technical terms, they are a family of population-based trial and error problem solvers with a metaheuristic or stochastic optimization character. In evolutionary computation, an initial set of candidate solutions is generated and iteratively updated. Each new generation is produced by stochastically removing less desired solutions, and introducing small random changes as well as, depending on the method, mixing parental information. In biological terminology, a population of solutions is subjected to natural selection (or artificial selection), mutation and possibly recombination. These biological functions serve as role models for the genetic operators - mutation, crossover, and selection - used in the EC procedures. As a result, the population will gradually evolve to increase in fitness, in this case the chosen fitness function of the algorithm. Evolutionary computation techniques can produce highly optimized solutions in a wide range of problem settings, making them popular in computer science. Many variants and extensions exist, suited to more specific families of problems and data structures. Evolutionary computation is also sometimes used in evolutionary biology as an in silico experimental procedure to study common aspects of general evolutionary processes. == History == The concept of mimicking evolutionary processes to solve problems originates before the advent of computers, such as when Alan Turing proposed a method of genetic search in 1948 . Turing's B-type u-machines resemble primitive neural networks, and connections between neurons were learnt via a sort of genetic algorithm. His P-type u-machines resemble a method for reinforcement learning, where pleasure and pain signals direct the machine to learn certain behaviors. However, Turing's paper went unpublished until 1968, and he died in 1954, so this early work had little to no effect on the field of evolutionary computation that was to develop. Evolutionary computing as a field began in earnest in the 1950s and 1960s. There were several independent attempts to use the process of evolution in computing at this time, which developed separately for roughly 15 years. Three branches emerged in different places to attain this goal: evolution strategies, evolutionary programming, and genetic algorithms. A fourth branch, genetic programming, eventually emerged in the early 1990s. These approaches differ in the method of selection, the permitted mutations, and the representation of genetic data. By the 1990s, the distinctions between the historic branches had begun to blur, and the term 'evolutionary computing' was coined in 1991 to denote a field that exists over all four paradigms. In 1962, Lawrence J. Fogel initiated the research of Evolutionary Programming in the United States, which was considered an artificial intelligence endeavor. In this system, finite state machines are used to solve a prediction problem: these machines would be mutated (adding or deleting states, or changing the state transition rules), and the best of these mutated machines would be evolved further in future generations. The final finite state machine may be used to generate predictions when needed. The evolutionary programming method was successfully applied to prediction problems, system identification, and automatic control. It was eventually extended to handle time series data and to model the evolution of gaming strategies. In 1964, Ingo Rechenberg and Hans-Paul Schwefel introduce the paradigm of evolution strategies in Germany. Since traditional gradient descent techniques produce results that may get stuck in local minima, Rechenberg and Schwefel proposed that random mutations (applied to all parameters of some solution vector) may be used to escape these minima. Child solutions were generated from parent solutions, and the more successful of the two was kept for future generations. This technique was first used by the two to successfully solve optimization problems in fluid dynamics. Initially, this optimization technique was performed without computers, instead relying on dice to determine random mutations. By 1965, the calculations were performed wholly by machine. John Henry Holland introduced genetic algorithms in the 1960s, and it was further developed at the University of Michigan in the 1970s. While the other approaches were focused on solving problems, Holland primarily aimed to use genetic algorithms to study adaptation and determine how it may be simulated. Populations of chromosomes, represented as bit strings, were transformed by an artificial selection process, selecting for specific 'allele' bits in the bit string. Among other mutation methods, interactions between chromosomes were used to simulate the recombination of DNA between different organisms. While previous methods only tracked a single optimal organism at a time (having children compete with parents), Holland's genetic algorithms tracked large populations (having many organisms compete each generation). By the 1990s, a new approach to evolutionary computation that came to be called genetic programming emerged, advocated for by John Koza among others. In this class of algorithms, the subject of evolution was itself a program written in a high-level programming language (there had been some previous attempts as early as 1958 to use machine code, but they met with little success). For Koza, the programs were Lisp S-expressions, which can be thought of as trees of sub-expressions. This representation permits programs to swap subtrees, representing a sort of genetic mixing. Programs are scored based on how well they complete a certain task, and the score is used for artificial selection. Sequence induction, pattern recognition, and planning were all successful applications of the genetic programming paradigm. Many other figures played a role in the history of evolutionary computing, although their work did not always fit into one of the major historical branches of the field. The earliest computational simulations of evolution using evolutionary algorithms and artificial life techniques were performed by Nils Aall Barricelli in 1953, with first results published in 1954. Another pioneer in the 1950s was Alex Fraser, who published a series of papers on simulation of artificial selection. As academic interest grew, dramatic increases in the power of computers allowed practical applications, including the automatic evolution of computer programs. Evolutionary algorithms are now used to solve multi-dimensional problems more efficiently than software produced by human designers, and also to optimize the design of systems. == Techniques == Evolutionary computing techniques mostly involve metaheuristic optimization algorithms. Broadly speaking, the field includes: Agent-based modeling Ant colony optimization Particle swarm optimization Swarm intelligence Artificial immune systems Artificial life Digital organism Cultural algorithms Differential evolution Dual-phase evolution Estimation of distribution algorithm Evolutionary algorithm Genetic algorithm Evolutionary programming Genetic programming Gene expression programming Grammatical evolution Evolution strategy Learnable evolution model Learning classifier system Memetic algorithms Neuroevolution Self-organization such as self-organizing maps, competitive learning Over recent years many dubious algorithms have been proposed, that are often just copies of existing algorithms (frequently Particle Swarm Optimization), where only the metaphor changed, but the algorithm itself is not new at all. A thorough catalogue with many of these dubious algorithms has been published in the Evolutionary Computation Bestiary. It is also important to note that many of these dubiously 'novel' algorithms have poor experimental validation. == Evolutionary algorithms == Evolutionary algorithms form a subset of evolutionary computation in that they generally only involve techniques implementing mechanisms inspired by biological evolution such as reproduction, mutation, recombination and natural selection. Candidate solutions to the optimization problem play the role of individuals in a population, and the cost function determines the environment within which the solutions "live" (see also fitness function). Evolution of the population then takes place after the repeated application of the above operators. In this process, there are two main forces that form the basis of evolutionary systems: Recombination (e.g. crossover) and mutation create the necessary diversity and thereby facilitate novelty, while selection acts as a force increasing quality. Many aspects of such an evolutionary process are stochastic. Changed pieces of information due to recombination and mutati

    Read more →
  • Suno (platform)

    Suno (platform)

    Suno is a generative artificial intelligence music creation platform. It is designed to generate music that can include vocals and instrumentation. The platform was initially developed by Suno, Inc., of Cambridge, Massachusetts. Suno has been widely available since December 20, 2023, after the launch of a web application and a partnership with Microsoft, which included Suno as a plugin in Microsoft Copilot. The program operates by producing songs based on text or audio prompts provided by its users. Suno does not disclose the dataset used to train its artificial intelligence. == History == Suno, Inc., was founded by four people: Michael Shulman, Georg Kucsko, Martin Camacho, and Keenan Freyberg. They all worked for Kensho, an AI startup, before starting their own company in Cambridge, Massachusetts. In April 2023, Suno released their open-source text-to-speech and audio model called "Bark" on GitHub. On March 21, 2024, Suno released its V3 version for all users. The new version allowed users to create a limited number of four-minute songs using a free account. Users can pay for more features. In April 2024, a sentimental ballad was generated with Suno based on the text of the MIT License. In June 2024, a lawsuit, led by the Recording Industry Association of America, was filed against Suno and Udio alleging widespread infringement of copyrighted sound recordings. The lawsuit sought to bar the companies from training on copyrighted music, as well as damages of up to $150,000 per work from infringements that have already taken place. On July 1, 2024, a mobile app for Suno was released. On November 19, 2024, Suno upgraded its AI song model program to v4. In January 2025, Michael Shulman remarked on a podcast, "I think the majority of people don't enjoy the majority of the time they spend making music." In March 2025, one day after thousands of musicians including Thom Yorke and ABBA's Björn Ulvaeus signed a letter calling for Suno to stop training its model on copyrighted music, Timbaland endorsed Suno in a video on the company's website. In July 2025, Suno user imoliver signed a record deal with Hallwood Media, which became the first instance of a traditional music label signing an AI-based creator. Hallwood later signed with AI-artist Xania Monet for US$3 million. Monet's songs were generated by Suno AI by poet Telisha Jones. In November 2025, Suno agreed to a $500 million dollar lawsuit settlement, in which Suno would be allowed to train its models on Warner Music Group's music catalog, and WMG would control aspects of AI likeness, music, audio, software, copyrights, AI tools and music created by users on Suno. As part of the settlement, Suno also acquired the concert discovery platform Songkick from WMG. == Controversy == Suno, Inc., has been sued by the Recording Industry Association of America for copyright infringement, and thousands of musicians have signed a letter demanding that the company cease using copyrighted music in their training data. Suno does not disclose the dataset used to train its artificial intelligence.

    Read more →
  • Felix, Net i Nika

    Felix, Net i Nika

    Felix, Net i Nika ("Felix, Net and Nika") is a series of Polish language science fiction books for teenagers, written by Rafał Kosik. It tells the adventures of three friends - Felix Polon, Net Bielecki and Nika Mickiewicz - who attend fictional Professor Kuszmiński Middle School in Warsaw. As of 2024, eighteen books have been published. == Books == There are currently 18 books in the series: Felix, Net and Nika and the Gang of Invisible People - November 2004. Felix, Net and Nika and the Theoretically Possible Catastrophe - November 2005 Felix, Net and Nika and the Palace of Dreams - November 2006 Felix, Net and Nika and the Trap of Immortality - November 2007 Felix, Net and Nika and the Orbital Conspiracy - November 2008 Felix, Net and Nika and the Orbital Conspiracy 2: Small Army - May 2009 Felix, Net and Nika and the Third Cousin - November 2009 Felix, Net and Nika and the Rebellion of Machines - March 2011 Felix, Net and Nika and the World Zero - November 2011 Felix, Net and Nika and the World Zero 2. Alternauts - November 2012 Felix, Net and Nika and the Extracurricular Stories - April 2013 Felix, Net and Nika and the Secret of Czerwona Hańcza - November 2013 Felix, Net and Nika and Curse of McKillian's House - November 2014 Felix, Net and Nika and (un)Safe Growing up - November 2015 Felix, Net and Nika and The End of The World as We Know It - November 2018 Felix, Net and Nika and No Chance - November 2022 Felix, Net and Nika and No Chance 2: other tomorrrow - 2023 Felix, Net and Nika and Fantology - June 2024 == Film == A feature motion picture, Felix, Net i Nika oraz Teoretycznie Możliwa Katastrofa (Felix, Net and Nika and the Theoretically Possible Catastrophe) was released in Poland on September 28, 2012. == Main characters == Felix Polon - a foresighted, fair-haired boy with dark brown eyes. He inherited the talent of constructing various things, especially robots, from his father- it saved his friends many times. He can make anything from nothing, always finds a way out of a situation; almost always has a plan. Together with his parents Marlene and Peter, grandmother Lucy, his dog Caban (a Black Russian Terrier) and Golem Golem a robot he built, Felix lives on Serdeczna Street in a small family house. Net Bielecki is quite tall & slim, has blue eyes and a high IQ level. "Net" is his nickname; his true name is unknown. He is the most trendy and 'awesome' in his entire class. He is a human calculator and is excellent in mathematics. He hates dictations and spelling because he is dyslexic. He is also quite lazy, absent-minded and sometimes hysterical, or panicking. His dark blond hair looks like a heap of hay after a grenade explosion. He is best in ICT and writes many of his own programs. His love interest is Nika Mickiewicz. Together with his parents Lila and Mark, and their newborn twins nicknamed Pompek and Prumcia he lives on the top floor of a Penthouse apartment. Nika Mickiewicz is a girl with a character. She is very brave and mature. She likes reading books. She has curly, red hair, green eyes and a few freckles. She is not very rich; she wears second-hand clothes and her only pair of black Dr. Martens shoes. She lives in a tiny apartment. She is an orphan, but hides that fact from people for almost 3 years. However, Felix and Net, her best and possibly only friends, find out about it. She also has abnormal abilities. She can move distant objects using her powers, ski uphill and knows some things by intuition. In other words, she is telekinetic. Manfred is a friendly AI program started and never finished by Net's father, and mastered and programmed further by Net himself. He likes going on adventures and solving mysteries with the trio much more than his actual job, which is controlling the traffic lights. He helped out the three friends many times and is their reliable and faithful friend. Morten is also an AI program, but he is the antagonist of the trio. He appears in all 6 books of Felix Net and Nika. In the first book, the trio thinks they finished him off for good, but as we find out later, he comes back in the third book. In the fifth/sixth book, he was the mastermind of the Orbital Conspiracy. Also, Morten's logo, appears in all 6 books and it is still a mystery what he has to do with each event.

    Read more →
  • Predicate (logic)

    Predicate (logic)

    In logic, a predicate is a non-logical symbol that represents a property or a relation, though, formally, does not need to represent anything at all. For instance, in the first-order formula P ( a ) {\displaystyle P(a)} , the symbol P {\displaystyle P} is a predicate that applies to the individual constant a {\displaystyle a} which evaluates to either true or false. Similarly, in the formula R ( a , b ) {\displaystyle R(a,b)} , the symbol R {\displaystyle R} is a predicate that applies to the individual constants a {\displaystyle a} and b {\displaystyle b} . Predicates are considered a primitive notion of first-order, and higher-order logic and are therefore not defined in terms of other more basic concepts. The term derives from the grammatical term "predicate", meaning a word or phrase that represents a property or relation. In the semantics of logic, predicates are interpreted as relations. For instance, in a standard semantics for first-order logic, the formula R ( a , b ) {\displaystyle R(a,b)} would be true on an interpretation if the entities denoted by a {\displaystyle a} and b {\displaystyle b} stand in the relation denoted by R {\displaystyle R} . Since predicates are non-logical symbols, they can denote different relations depending on the interpretation given to them. While first-order logic only includes predicates that apply to individual objects, other logics may allow predicates that apply to collections of objects defined by other predicates. Strictly speaking, a predicate does not need to be given any interpretation, so long as its syntactic properties are well-defined. For example, equality may be understood solely through its reflexive and substitution properties (cf. Equality (mathematics) § Axioms). Other properties can be derived from these, and they are sufficient for proving theorems in mathematics. Similarly, set membership can be understood solely through the axioms of Zermelo–Fraenkel set theory. == Predicates in different systems == A predicate is a statement or mathematical assertion that contains variables, sometimes referred to as predicate variables, and may be true or false depending on those variables’ value or values. In propositional logic, atomic formulas are sometimes regarded as zero-place predicates. In a sense, these are nullary (i.e. 0-arity) predicates. In first-order logic, a predicate is a non-logical relation symbol, which forms an atomic formula when applied to an appropriate number of terms. In set theory with the law of excluded middle, predicates are understood to be characteristic functions or set indicator functions (i.e., functions from a set element to a truth value). Set-builder notation makes use of predicates to define sets. In autoepistemic logic, which rejects the law of excluded middle, predicates may be true, false, or simply unknown. In particular, a given collection of facts may be insufficient to determine the truth or falsehood of a predicate. In fuzzy logic, the strict true/false valuation of the predicate is replaced by a quantity interpreted as the degree of truth.

    Read more →
  • Smart speaker

    Smart speaker

    A smart speaker is a type of loudspeaker and voice command device with an integrated virtual assistant that offers interactive actions and hands-free activation with the help of one "wake word" (or several "wake words"). Some smart speakers also act as smart home hubs by using Wi-Fi, Bluetooth, Thread, and other protocol standards to extend usage beyond audio playback and control home automation devices connected through a local area network. == History == Early voice-activated devices began in 2013 with MIT's Jasper project, which used multiple microphones and cloud software to power hands-free interactions from across a room. The first commercial smart speaker was the Amazon Echo, which was released in 2014 powered by Alexa and a ring of far-field microphones. Google followed in 2016 with Home, powered by Google Assistant. By 2017, devices like the Echo Show and Home Hub (later called Nest Hub) added touchscreens and video, creating the "smart display" subcategory. In 2018, Apple joined the smart speaker trend by launching the HomePod, which focused on high-quality audio alongside their built-in assistant Siri. ASUS release its own smart Speaker Xiao-Bu in 2019 with Artificial Intelligence, it terminates the Cloud Service on June 1st, 2025, which means all real-time service such as weather, news, currency conversion is affected. Sonos's 1st smart speaker Sonos One released in 2017, powered by Alexa. Invoke by Harman Kardon was powered by Microsoft's intelligent personal assistant, Cortana. In the early 2020s, smart speakers gained on-device voice processing for faster responses and improved privacy. New standards such as Matter and Thread allowed multitudes of smart-home devices (even from completely different brands) to work together. == Features == === Audio and Voice === Smart speakers use multiple microphones along with noise-cancelling software to pick up your voice from across the room, even when music is playing or the assistant is already talking. Noise suppression and echo cancellation is also used by the speaker so it can focus in on who is talking and ignore any background noises. Most smart speaker models can recognize who is speaking by voiceprint, which allows the speaker to grab information from that person's calendar, preferences, or music playlists. Listening to music on a speaker is when importance for good audio quality becomes apparent. Entry-level (cheaper) speakers such as the Home Mini or the Echo Dot have a single full-range driver. These lower-end speakers typically aren't great for listening to music as the audio quality is pretty poor. More advanced units such as the Home Max or Echo Studio have separate tweeters and woofers meant for listening to music in high quality. === Connectivity and smart-home control === Most connect over Wi-Fi or Bluetooth and support hub protocols like Thread and Matter. That lets them not only stream and play music but also allows you to control various brands of smart lights, thermostats, door locks, cameras, and much more-all from one point of control. Each can have its own designated interface and features in-house, usually launched or controlled via application or home automation software. These devices are able to communicate with each other via peer-to-peer connection through mesh networking. These speakers and related smart devices are typically controlled with one smartphone application. === Assistant services and skills === The built-in assistants handle timers, alarms, reminders, news briefings, weather updates, send messages to other smart devices, send texts, make calls, and simple questions. You can combine actions together in what are typically known as routines (for example saying "good morning" turns on lights, starts the coffee, says the weather, and reads the news) and add extra functions known as skills or actions (for things like ordering food or playing trivia games). This hands-free use of smart speakers can help assist those with disabilities. Most other technologies need the user to be able to physically interact with the device. Smart speakers are not bound by these limitations and can serve as an excellent tool for those who are unable to use their arms or legs or have vision issues. Although these tasks can be completed by a phone or computer, consumers tend to lean towards smart speakers due to factors such as their range being much greater than that of a phone and the need to not have to physically interact with the speaker to get the voice assistant as with most smartphones, certain parts of a phone may need to be interacted with to activate the speaking assistant. === Smart displays === Some smart speakers also include a screen to show the user a visual response. A smart speaker with a touchscreen is known as a smart display; these integrate a conversational user interface with display screens to augment voice interaction with images and video. They are powered by one of the common voice assistants and offer additional controls for smart home devices, feature streaming apps, and web browsers with touch controls for selecting content. The first smart displays were introduced in 2017 by Amazon (Amazon Echo Show) and Google (Google/Nest Home Hub). Hotel chain Marriott International partnered with Amazon to install Echo devices in select hotels since 2018. A Taiwanese startup, Aiello, launched the Aiello Voice Assistant (AVA) in the Asian hotel market in 2019, claiming it is powered by a multi-AI model system. Angie by Nomadix, which is similar to the Amazon Echo, launched its first product in 2017, specifically targeting hotel properties in the North America. In May 2019, Angie Hospitality acquired the assets of Roxy, a competitor that also built its own speech-enabled virtual assistant technology for hotels. This acquisition merged two proprietary NLP stacks into the current Nomadix product. === Artificial intelligence === The newest speakers can use on-device AI or cloud-based generative models to allow the smart speaker to carry on much more natural conversations, draft emails or recipes, suggest ideas based on context, or even create short pieces of music or art. This AI evolution allows these speakers to do far more than what they could do before. == Accuracy == According to a study by Proceedings of the National Academy of Sciences of the United States of America released In March 2020, the six biggest tech development companies, Amazon, Apple, Google, Yandex, IBM and Microsoft, have misidentified more words spoken by "black people" than "white people". The systems tested errors and unreadability, with a 19 and 35 percent discrepancy for the former and a 2 and 20 percent discrepancy for the latter. The North American Chapter of the Association for Computational Linguistics (NAACL) also identified a discrepancy between male and female voices. According to their research, Google's speech recognition software is 13 percent more accurate for men than women. It performs better than the systems used by Bing, AT&T, and IBM. == Privacy concerns == The built-in microphone in smart speakers is continuously listening for wake words followed by a command. However, these continuously listening microphones also raise privacy concerns among users. According to a survey taken by 1,007 people in Western Europe, it is clear that privacy is the biggest concern holding consumers back from buying "smart" products. these concerns include what is being recorded, how the data will be used, how it will be protected, and whether it will be used for invasive advertising. Furthermore, an analysis of Amazon Echo Dots showed that 30–38% of "spurious audio recordings were human conversations", suggesting that these devices capture audio other than strictly detection of the wake word. === As a wiretap === There are strong concerns that the ever-listening microphone of smart speakers presents a perfect candidate for wiretapping. In 2017, British security researcher Mark Barnes showed that pre-2017 Echos have exposed pins which allow for a compromised OS to be booted. According to Umar Iqbal, an assistant professor at Washington University in St. Louis, research indicates that data from consumer interactions with Alexa was used to targeted advertisements and products to consumer with over 40% of transmitted data lacking proper encryption raising privacy concerns. Further data indicates that due to the Smart Speakers ability to always capture audio, it begins to pick up on external conversations from consumers not related to commands given to the smart speaker. Things such as other members in the household, consumers on the phone and even TV audio can be picked up by these speakers and stored for future use by companies. === Voice assistance vs privacy === While voice assistants provide a valuable service, there can be some hesitation towards using them in various social contexts, such as in public or around other users. However, only more recently have users begun interac

    Read more →
  • Speech recognition

    Speech recognition

    Speech recognition (automatic speech recognition (ASR), computer speech recognition, or speech-to-text (STT)) is a sub-field of computational linguistics concerned with methods and technologies that translate spoken language into text or other interpretable forms. Speech recognition applications include voice user interfaces, where the user speaks to a device, which "listens" and processes the audio. Common voice applications include interpreting commands for calling, call routing, home automation, and aircraft control. These applications are called direct voice input. Productivity applications include searching audio recordings, creating transcripts, and dictation. Speech recognition can be used to analyse speaker characteristics, such as identifying native language using pronunciation assessment. Voice recognition (speaker identification) refers to identifying the speaker, rather than speech contents. Recognizing the speaker can simplify the task of translating speech in systems trained on a specific person's voice. It can also be used to authenticate the speaker as part of a security process. == History == Applications for speech recognition developed over many decades, with progress accelerated due to advances in deep learning and the use of big data. These advances are reflected in an increase in academic papers, and greater system adoption. Key areas of growth include vocabulary size, more accurate recognition for unfamiliar speakers (speaker independence), and faster processing speed. === Pre-1970 === 1952 – Bell Labs researchers, Stephen Balashek, R. Biddulph, and K. H. Davis, built Audrey for single-speaker digit recognition. Their system located the formants in the power spectrum of each utterance. 1960 – Gunnar Fant developed and published the source–filter model of speech production. 1962 – IBM's 16-word "Shoebox" machine's speech recognition debuted at the 1962 World's Fair. 1966 – Linear predictive coding, a speech coding method, was proposed by Fumitada Itakura of Nagoya University and Shuzo Saito of Nippon Telegraph and Telephone. 1969 – Funding at Bell Labs came to a halt for several years after the company's head engineer, John R. Pierce, wrote an open letter criticizing speech recognition research. This defunding lasted until Pierce retired and James L. Flanagan took over. Raj Reddy was the first person to work on continuous speech recognition, as a graduate student at Stanford University in the late 1960s. Previous systems required users to pause after each word. Reddy's system issued spoken commands for playing chess. Around this time, Soviet researchers invented the dynamic time warping (DTW) algorithm and used it to create a recognizer capable of operating on a 200-word vocabulary. DTW processed speech by dividing it into short frames (e.g. 10 ms segments) and treating each frame as a unit. Speaker independence, however, remained unsolved. === 1970–1990 === 1971 – DARPA funded a five-year speech recognition research project, Speech Understanding Research, seeking a minimum vocabulary size of 1,000 words. The project considered speech understanding a key to achieving progress in speech recognition, which was later disproved. BBN, IBM, Carnegie Mellon (CMU), and Stanford Research Institute participated. 1972 – The IEEE Acoustics, Speech, and Signal Processing group held a conference in Newton, Massachusetts. 1976 – The first ICASSP was held in Philadelphia, which became a major venue for publishing on speech recognition. During the late 1960s, Leonard Baum developed the mathematics of Markov chains at the Institute for Defense Analysis. A decade later, at CMU, Raj Reddy's students James Baker and Janet M. Baker began using the hidden Markov model (HMM) for speech recognition. James Baker had learned about HMMs while at the Institute for Defense Analysis. HMMs enabled researchers to combine sources of knowledge, such as acoustics, language, and syntax, in a unified probabilistic model. By the mid-1980s, Fred Jelinek's team at IBM created a voice-activated typewriter called Tangora, which could handle a 20,000-word vocabulary. Jelinek's statistical approach placed less emphasis on emulating human brain processes in favor of statistical modelling. (Jelinek's group independently discovered the application of HMMs to speech.) This was controversial among linguists since HMMs are too simplistic to account for many features of human languages. However, the HMM proved to be a highly useful way for modelling speech and replaced dynamic time warping as the dominant speech recognition algorithm in the 1980s. 1982 – Dragon Systems, founded by James and Janet M. Baker, was one of IBM's few competitors. === Practical speech recognition === The 1980s also saw the introduction of the n-gram language model. 1987 – The back-off model enabled language models to use multiple-length n-grams, and CSELT used HMM to recognize languages (in software and hardware, e.g. RIPAC). At the end of the DARPA program in 1976, the best computer available to researchers was the PDP-10 with 4 MB of RAM. It could take up to 100 minutes to decode 30 seconds of speech. Practical products included: 1984 – the Apricot Portable was released with up to 4096 words support, of which only 64 could be held in RAM at a time. 1987 – a recognizer from Kurzweil Applied Intelligence 1990 – Dragon Dictate, a consumer product released in 1990. AT&T deployed the Voice Recognition Call Processing service in 1992 to route telephone calls without a human operator. The technology was developed by Lawrence Rabiner and others at Bell Labs. By the early 1990s, the vocabulary of the typical commercial speech recognition system had exceeded the average human vocabulary. Reddy's former student, Xuedong Huang, developed the Sphinx-II system at CMU. Sphinx-II was the first to do speaker-independent, large vocabulary, continuous speech recognition, and it won DARPA's 1992 evaluation. Handling continuous speech with a large vocabulary was a major milestone. Huang later founded the speech recognition group at Microsoft in 1993. Reddy's student Kai-Fu Lee joined Apple, where, in 1992, he helped develop the Casper speech interface prototype. Lernout & Hauspie, a Belgium-based speech recognition company, acquired other companies, including Kurzweil Applied Intelligence in 1997 and Dragon Systems in 2000. L&H was used in Windows XP. L&H was an industry leader until an accounting scandal destroyed it in 2001. L&H speech technology was bought by ScanSoft, which became Nuance in 2005. Apple licensed Nuance software for its digital assistant Siri. ==== 2000s ==== In the 2000s, DARPA sponsored two speech recognition programs: Effective Affordable Reusable Speech-to-Text (EARS) in 2002, followed by Global Autonomous Language Exploitation (GALE) in 2005. Four teams participated in EARS: IBM; a team led by BBN with LIMSI and the University of Pittsburgh; Cambridge University; and a team composed of ICSI, SRI, and the University of Washington. EARS funded the collection of the Switchboard telephone speech corpus, which contained 260 hours of recorded conversations from over 500 speakers. The GALE program focused on Arabic and Mandarin broadcast news. Google's first effort at speech recognition came in 2007 after recruiting Nuance researchers. Its first product, GOOG-411, was a telephone-based directory service. Since at least 2006, the U.S. National Security Agency has employed keyword spotting, allowing analysts to index large volumes of recorded conversations and identify speech containing "interesting" keywords. Other government research programs focused on intelligence applications, such as DARPA's EARS program and IARPA's Babel program. In the early 2000s, speech recognition was dominated by hidden Markov models combined with feed-forward artificial neural networks (ANN). Later, speech recognition was taken over by long short-term memory (LSTM), a recurrent neural network (RNN) published by Sepp Hochreiter & Jürgen Schmidhuber in 1997. LSTM RNNs avoid the vanishing gradient problem and can learn "Very Deep Learning" tasks that require memories of events that happened thousands of discrete time steps earlier, which is important for speech. Around 2007, LSTMs trained with Connectionist Temporal Classification (CTC) began to outperform. In 2015, Google reported a 49 percent error‑rate reduction in its speech recognition via CTC‑trained LSTM. Transformers, a type of neural network based solely on attention, were adopted in computer vision and language modelling, and then to speech recognition. Deep feed-forward (non-recurrent) networks for acoustic modelling were introduced in 2009 by Geoffrey Hinton and his students at the University of Toronto, and by Li Deng and colleagues at Microsoft Research. In contrast to the prioer incremental improvements, deep learning decreased error rates by 30%. Both shallow and deep forms (e.g., recurrent nets) of ANNs had been explored since the 1980s. Howev

    Read more →
  • Monkey and banana problem

    Monkey and banana problem

    The monkey and banana problem is a famous toy problem in artificial intelligence, particularly in logic programming and planning. It has been framed as: A monkey is in a room containing a box and a bunch of bananas. The bananas are hanging from the ceiling out of reach of the monkey. How can the monkey obtain the bananas? The situation is used as a toy problem for computer science and can be solved with an expert system such as CLIPS. The example set of rules that CLIPS provides is somewhat fragile, in that, naive changes to the rulebase that might seem to a human of average intelligence to make common sense can cause the engine to fail to get the monkey to reach the banana. Other examples exist using Rules Based System (RBS), including a project implemented in Python.

    Read more →
  • Asian Digital Finance Forum & Awards

    Asian Digital Finance Forum & Awards

    Asian Digital Finance Forum & Awards (also known as Asian Digital Finance Forum and Awards) is a forum and honorary awards platform convened in Colombo, Sri Lanka. It has been hosted in a hybrid format (virtual and in-person), with editions reported in 2022, 2023 and 2025. The event is organised by the Asian FinTech Academy (AFTA) in collaboration with a number of local and international institutions. == Overview == The forum has featured international academic, industry, and policy speakers and has recognised institutions and individuals for contributions related to digital finance and fintech innovation. Media coverage has described participation and recognition at the forum as spanning multiple regions, with institutions and individuals from South Asia, Southeast Asia, East Asia, the Middle East, Europe, and North America featured across different editions. == Awards and recognition == The forum and awards were held in a hybrid format with virtual and in-person proceedings at Hilton Colombo in the 2022 and 2023 editions. The Asian Digital Finance Forum & Awards presents honorary recognitions to institutions and individuals for contributions to digital finance, financial inclusion, and related regulatory, technological, and policy developments. Media coverage has described the recognitions as non-competitive and based on demonstrated leadership and impact rather than open nominations. In 2025, the forum and awards served as an anchor initiative associated with the Asia International Digital Economy & AI in Finance Summit at Port City Colombo, with an emphasis on artificial intelligence in finance, financial inclusion, and governance-related themes. === 2022 === According to reporting by Daily FT, institutions recognised at the 2022 edition included Sri Lanka’s Bank of Ceylon, Commercial Bank of Ceylon, Hatton National Bank, and People’s Bank, alongside international organisations and fintech-sector contributors. === 2023 === Coverage of the 2023 forum described recognitions awarded to India’s International Financial Services Centres Authority (IFSCA) for regulatory innovation, as well as to digital finance and payments platforms including Dialog Genie and SLT-Mobitel mCash. IDEMIA’s Asia–Pacific operations were also recognised for contributions related to biometric and digital identity technologies in financial services. === 2025 === For the 2025 edition, institutional honourees reported in the media included Nium (Singapore), recognised for cross-border payments optimisation, and Paytm (India), recognised for AI-powered financial inclusion initiatives. A Visionary Award for Next-Generation Financial Hub Development was presented to Port City Colombo in recognition of its fintech- and AI-oriented development strategy. Individual honourees reported for 2025 included Sopnendu Mohanty (Singapore), Neil Tan (Hong Kong), Purvi Munot (United Arab Emirates), and Amira Abdelaziz (Egypt), recognised for contributions spanning fintech governance, ecosystem development, inclusive wealth technology, and AI-driven financial policy and regulation. In 2025, media reports described the awards as being subject to an independent validation framework. The process was led by Dr. Sivaguru S. Sritharan, appointed as Global Validation Chair, and involved independent research, analytical review, and benchmarking against international standards, with recognitions characterised as honorary and non-competitive.

    Read more →