AI Chatbot Creator

AI Chatbot Creator — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

CEITON

CEITON is a web-based software system for facilitating and automating business processes such as planning, scheduling, and payroll using workflow technologies. The system is used by several media companies such as MDR, Yle, RAI and Red Bull Media House. In December 2018, the first CEITON User Group Meeting took place in Leipzig, Germany. == Architecture == The software runs on a server (on premises) or in the cloud and is scalable on parallel servers. Data security is warranted by role-based access control (RBAC). The software is used via web-browsers and not dependent on particular system software. == Structure and Features == CEITON combines the two classical approaches of production planning and control and workflow management. === Project Management === The scheduling system plans, manages, bills, and analyzes projects or tasks. It manages human and technical resources, material, and locations on a single GUI. The system uses a gantt chart to assign tasks to be done to available and eligible resources (i.e. staff), automatically or by drag-and-drop. The scheduling module includes material management, resource management/ human resource management, integration of freelancers, clients and suppliers, long-term budget planning, time-tracking, shift scheduling, quality management, delivery and logistics, document management, archive, analysis and controlling, business reporting, as well as all accounting and documentation processes. === Workflow === The workflow management system module coordinates business processes. Processes are defined once as a workflow and then repeatedly executed. Human resources are automatically assigned to steps (tasks) and integrated in workflow forms. Systems are integrated with an EAI/SOAP module, allowing data exchange with arbitrary external systems which are also involved in the business process. It also features a 3-D workflow overview in which the status of each project step can be determined by its color in the overview. === Process Management === For project and order processing management, business processes are designed as workflows, and coordinate communication automatically. Different user interfaces for staff, customers or suppliers can be created so each gets only relevant information. Different workflow forms are associated with different log-ins. The main application for the system is knowledge-based business processes, in which many people are involved and virtual results are produced, e.g. in research, or development of media products, such as TV and movies. Broadcasters and media companies such as MDR and Yle use CEITON to control their production processes for products and services and coordinate complex workflows with all kinds of resources. === Integrations === An integrated EAI module allows CEITON to integrate every external system in any business process without programming, using SOAP and similar technologies. Aspera and FileCatalyst were integrated for faster data transfer, yet complex ERP systems and numerous SAP modules have also been integrated, for example, to extract working times to payroll. === Mobile Working === Since Version 7, released in 2015, CEITON includes a time-tracking module allowing employees to enter their times from mobile devices such as tablets running Android, iPhones etc. == History == Ceiton Technologies (SME tech firm), the company developing CEITON, was founded in Leipzig, Germany in 2000, staffing solutions for the Bureau of Internal Revenue in Manila, Philippines, were implemented in 2000 together with the Deutsche Gesellschaft für Technische Zusammenarbeit of the German government. The first version (1.0) of the software was released in July 2001. The product was originally developed for German broadcasting companies. CEITON is named after the Japanese concept Seiton, one of the principles of Japanese workplace design methodology known as 5S. Since version 7, released in 2015, CEITON includes a time-tracking module allowing employees to enter their times from mobile devices such as tablets running Android, iPhones etc. In May 2005 CEITON won the IQ innovation award, sponsored by Siemens, in the category Excellent innovation in the IT-sector. Since 2007, CEITON has been present at the broadcast trade fairs NAB in Las Vegas and IBC in Amsterdam. In 2020, the company celebrated its 20th anniversary.
Read more →
Protégé (software)

Protégé is a free, open source ontology editor and a knowledge management system. The Protégé meta-tool was first built by Mark Musen in 1987 and has since been developed by a team at Stanford University. The software is the most popular and widely used ontology editor in the world. == Overview == Protégé provides a graphical user interface to define ontologies. It also includes deductive classifiers to validate that models are consistent and to infer new information based on the analysis of an ontology. Like Eclipse, Protégé is a framework for which various other projects suggest plugins. This application is written in Java and makes heavy use of Swing to create the user interface. According to their website, there are over 300,000 registered users. A 2009 book calls it "the leading ontological engineering tool". Protégé is developed at Stanford University and is made available under the BSD 2-clause license. Earlier versions of the tool were developed in collaboration with the University of Manchester.
Read more →
Mind map

A mind map is a diagram used to visually organize information into a hierarchy, showing relationships among pieces of the whole. It is often based on a single concept, drawn as an image in the center of a blank page, to which associated representations of ideas such as images, words and parts of words are added. Major ideas are connected directly to the central concept, and other ideas branch out from those major ideas. Mind maps can also be drawn by hand, either as "notes" during a lecture, meeting or planning session, for example, or as higher quality pictures when more time is available. Mind maps are considered to be a type of spider diagram. == Origin == Although the term "mind map" was first popularized by British popular psychology author and television personality Tony Buzan, the use of diagrams that visually "map" information using branching and radial maps traces back centuries. These pictorial methods record knowledge and model systems, and have a long history in learning, brainstorming, memory, visual thinking, and problem solving by educators, engineers, psychologists, and others. Some of the earliest examples of such graphical records were developed by Porphyry of Tyros, a noted thinker of the 3rd century, as he graphically visualized the concept categories of Aristotle. Philosopher Ramon Llull (1235–1315) also used such techniques. Buzan's specific approach, and the introduction of the term "mind map", started with a 1974 BBC TV series he hosted, called Use Your Head. In this show, and companion book series, Buzan promoted his conception of radial tree, diagramming key words in a colorful, radiant, tree-like structure. == Differences from other visualizations == Concept maps: Mind maps differ from concept maps in that mind maps are based on a radial hierarchy (tree structure) denoting relationships with a central concept, whereas concept maps can be more free-form, based on connections between concepts in more diverse patterns. Also, concept maps typically have text labels on the links between nodes. However, either can be part of a larger personal knowledge base system. Modeling graphs or graphical modeling languages: There is no rigorous right or wrong with mind maps, which rely on the arbitrariness of mnemonic associations to aid people's information organization and memory. In contrast, a modeling graph such as a UML diagram structures elements using a precise standardized iconography to aid the design of systems. == Research == === Effectiveness === Cunningham (2005) conducted a user study in which 80% of the students thought "mindmapping helped them understand concepts and ideas in science". Other studies also report some subjective positive effects of the use of mind maps. Positive opinions on their effectiveness, however, were much more prominent among students of art and design than in students of computer and information technology, with 62.5% vs 34% (respectively) agreeing that they were able to understand concepts better with mind mapping software. Farrand, Hussain, and Hennessy (2002) found that spider diagrams (similar to concept maps) had limited, but significant, impact on memory recall in undergraduate students (a 10% increase over baseline for a 600-word text only) as compared to preferred study methods (a 6% increase over baseline). This improvement was only robust after a week for those in the diagram group and there was a significant decrease in motivation compared to the subjects' preferred methods of note taking. A meta study about concept mapping concluded that concept mapping is more effective than "reading text passages, attending lectures, and participating in class discussions". The same study also concluded that concept mapping is slightly more effective "than other constructive activities such as writing summaries and outlines". However, results were inconsistent, with the authors noting "significant heterogeneity was found in most subsets". In addition, they concluded that low-ability students may benefit more from mind mapping than high-ability students. === Features === Joeran Beel and Stefan Langer conducted a comprehensive analysis of the content of mind maps. They analysed 19,379 mind maps from 11,179 users of the mind mapping applications SciPlore MindMapping (now Docear) and MindMeister. Results include that average users create only a few mind maps (mean=2.7), average mind maps are rather small (31 nodes) with each node containing about three words (median). However, there were exceptions. One user created more than 200 mind maps, the largest mind map consisted of more than 50,000 nodes and the largest node contained ~7,500 words. The study also showed that between different mind mapping applications (Docear vs MindMeister) significant differences exist related to how users create mind maps. === Automatic creation === There have been some attempts to create mind maps automatically. Brucks & Schommer created mind maps automatically from full-text streams. Rothenberger et al. extracted the main story of a text and presented it as mind map. There is also a patent application about automatically creating sub-topics in mind maps. == Tools == Mind-mapping software can be used to organize large amounts of information, combining spatial organization, dynamic hierarchical structuring and node folding.Software packages can extend the concept of mind-mapping by allowing individuals to map more than thoughts and ideas with information on their computers and the Internet, like spreadsheets, documents, Internet sites, images and videos. It has been suggested that mind-mapping can improve learning/study efficiency up to 15% over conventional note-taking. == Gallery == The following dozen examples of mind maps show the range of styles that a mind map may take, from hand-drawn to computer-generated and from mostly text to highly illustrated. Despite their stylistic differences, all of the examples share a tree structure that hierarchically connects sub-topics to a main topic.
Read more →
AlphaFold

AlphaFold is an artificial intelligence (AI) program developed by DeepMind, a subsidiary of Alphabet, which performs predictions of protein structure. It is designed using deep learning techniques. AlphaFold 1 (2018) placed first in the overall rankings of the 13th Critical Assessment of Structure Prediction (CASP) in December 2018. It was particularly successful at predicting the most accurate structures for targets rated as most difficult by the competition organizers, where no existing template structures were available from proteins with partially similar sequences. AlphaFold 2 (2020) repeated this placement in the CASP14 competition in November 2020. It achieved a level of accuracy much higher than any other entry. It scored above 90 on CASP's global distance test (GDT) for approximately two-thirds of the proteins, a test measuring the similarity between a computationally predicted structure and the experimentally determined structure, where 100 represents a complete match. The inclusion of metagenomic data has improved the quality of the prediction of multiple sequence alignments. One of the biggest sources of the training data was the custom-built Big Fantastic Database of 65,983,866 protein families, represented as multiple sequence alignments and Hidden Markov models, covering 2,204,359,010 protein sequences from reference databases, metagenomes, and metatranscriptomes. AlphaFold 2's results at CASP14 were described as "astounding" and "transformational". However, some researchers noted that the accuracy was insufficient for a third of its predictions, and that it did not reveal the underlying mechanism or rules of protein folding for the protein folding problem, which remains unsolved. Despite this, the technical achievement was widely recognized. On 15 July 2021, the AlphaFold 2 paper was published in Nature as an advance access publication alongside open source software and a searchable database of species proteomes. As of November 2025, the paper had been cited nearly 43,000 times. AlphaFold 3 was announced on 8 May 2024. It can predict the structure of complexes created by proteins with DNA, RNA, various ligands, and ions. The new prediction method shows a minimum 50% improvement in accuracy for protein interactions with other molecules compared to existing methods. Demis Hassabis and John Jumper shared one half of the 2024 Nobel Prize in Chemistry, awarded "for protein structure prediction," while the other half went to David Baker "for computational protein design." Hassabis and Jumper had previously won the Breakthrough Prize in Life Sciences and the Albert Lasker Award for Basic Medical Research in 2023 for their leadership of the AlphaFold project. == Background == Proteins consist of chains of amino acids which spontaneously fold to form the three dimensional (3-D) structures of the proteins. The 3-D structure is crucial to understanding the biological function of the protein. Protein structures can be determined experimentally through techniques such as X-ray crystallography, cryo-electron microscopy and nuclear magnetic resonance (NMR), which are all expensive and time-consuming. Such efforts, using the experimental methods, have identified the structures of about 170,000 proteins over the last 60 years, while there are over 200 million known proteins across all life forms. Over the years, researchers have applied numerous computational methods to predict the 3D structures of proteins from their amino acid sequences, accuracy of such methods in best possible scenario is close to experimental techniques (NMR) by the use of homology modeling based on molecular evolution. CASP, which was launched in 1994 to challenge the scientific community to produce their best protein structure predictions, found that GDT scores of only about 40 out of 100 can be achieved for the most difficult proteins by 2016. AlphaFold started competing in the 2018 CASP using an artificial intelligence (AI) deep learning technique. == Algorithm == DeepMind is known to have trained the program on over 170,000 protein structures from the Protein Data Bank, a public repository of protein sequences and structures. The program uses a form of attention network, a deep learning technique that focuses on having the AI identify parts of a larger problem, then piece it together to obtain the overall solution. The overall training was conducted on processing power between 100 and 200 GPUs. === AlphaFold 1 (2018) === AlphaFold 1 (2018) was built on work developed by various teams in the 2010s, work that looked at the large databases of related protein sequences now available from many different organisms (most without known 3D structures), to try to find changes at different residues (peptides) that appeared to be correlated, even though the residues were not consecutive in the main chain. Such correlations suggest that the residues may be close to each other physically, even though not close in the sequence, allowing a contact map to be estimated. Building on recent work prior to 2018, AlphaFold 1 extended this by estimating a probability distribution for the distances between residues, effectively transforming the contact map into a distance map. It also used more advanced learning methods than previously to develop the inference. The code was not made publicly available, except to run on sequences of proteins in the 2018 CASP competition. === AlphaFold 2 (2020) === The 2020 version of the program (AlphaFold 2, 2020) is significantly different from the original version that won CASP 13 in 2018, according to the team at DeepMind. AlphaFold 1 used a number of separately trained modules to produce a guide potential, which was then combined with a physics-based energy potential. AlphaFold 2 replaced this with a system of interconnected sub-networks, forming a single, differentiable, end-to-end model based on pattern recognition. This model was trained in an integrated manner. After the neural network's prediction converges, a final refinement step applies local physical constraints using energy minimization based on the AMBER force field. This step only slightly adjusts the predicted structure. A key part of the 2020 system are two modules, believed to be based on a transformer design, which are used to progressively refine a vector of information for each relationship (or "edge" in graph-theory terminology) between an amino acid residue of the protein and another amino acid residue (these relationships are represented by the array shown in green); and between each amino acid position and each different sequences in the input sequence alignment (these relationships are represented by the array shown in red). Internally these refinement transformations contain layers that have the effect of bringing relevant data together and filtering out irrelevant data (the "attention mechanism") for these relationships, in a context-dependent way, learned from training data. These transformations are iterated, the updated information output by one step becoming the input of the next, with the sharpened residue/residue information feeding into the update of the residue/sequence information, and then the improved residue/sequence information feeding into the update of the residue/residue information. As the iteration progresses, according to one report, the "attention algorithm ... mimics the way a person might assemble a jigsaw puzzle: first connecting pieces in small clumps—in this case clusters of amino acids—and then searching for ways to join the clumps in a larger whole." The output of these iterations then informs the final structure prediction module, which also uses transformers, and is itself then iterated. In an example presented by DeepMind, the structure prediction module achieved a correct topology for the target protein on its first iteration, scored as having a GDT_TS of 78, but with a large number (90%) of stereochemical violations – i.e. unphysical bond angles or lengths. With subsequent iterations the number of stereochemical violations fell. By the third iteration the GDT_TS of the prediction was approaching 90, and by the eighth iteration the number of stereochemical violations was approaching zero. The training data was originally restricted to single peptide chains. However, the October 2021 update, named AlphaFold-Multimer, included protein complexes in its training data. DeepMind stated this update succeeded about 70% of the time at accurately predicting protein-protein interactions. === AlphaFold 3 (2024) === Announced on 8 May 2024, AlphaFold 3 was co-developed by Google DeepMind and Isomorphic Labs, both subsidiaries of Alphabet. AlphaFold 3 is not limited to proteins, as it can also predict the structures of protein complexes with DNA, RNA, post-translational modifications and selected ligands and ions. AlphaFold 3 introduces the "Pairformer," a deep learning architecture inspired by the transformer, which is considered similar to, but si
Read more →
VOCEDplus

VOCEDplus is a free international research database about tertiary education, maintained and developed by staff at the c (NCVER) in Adelaide, South Australia. The focus of the database content is the relation of post-compulsory education and training to workforce needs, skills development, and social inclusion. == Structure == The content of the VOCEDplus database encompasses vocational education and training (VET), higher education, lifelong learning, informal learning, VET in schools, adult and community education, apprenticeships/traineeships, international education, providers of education and training, and workforce development. It is international in scope and contains over 84,000 English language records, many with links to full text documents. VOCEDplus contains extensive Australian materials and includes a wide range of international information, covering outcomes of tertiary education in the shape of published research, practice, policy, and statistics. Entries are included for the following types of publications: reports; annual reports; papers; discussion papers; occasional papers; working papers; books; book chapters; conference papers; conference proceedings; journals; journal articles; policy documents; published statistics; theses; podcasts; and teaching and training materials. Each database entry contains standard bibliographic information and an abstract. Many entries include full text access via the publisher's website or a digitised copy. == History == === 1989-1997 === In the early years VOCEDplus was known as VOCED. The original database was produced by a network of clearinghouses across Australia with the aim of sharing activities in the technical and further education (TAFE) sector. VOCED was produced in hardcopy and an electronic version was distributed on diskette. === 1997-2001 === 1997 - the first web version of VOCED was made available from the National Centre for Vocational Education Research (NCVER) organisational website 1998 - a major project to upgrade the database and expand its international coverage commenced 2001 - creation of VOCED's own website 2001 - VOCED endorsed as the UNESCO international database for technical and vocational education and training (TVET) research information === 2001-2009 === Many changes to the database and website occurred during this period with a focus on continuous improvement to meet the needs of users and utilise emerging technologies. 2006 - materials produced for two adult literacy and learning programs funded by the Australian Department of Education, Employment and Workplace Relations (DEEWR) - the Workplace English Language and Learning (WELL) Programme and the Adult Literacy National Project (ALNP) included in VOCED 2007 - the Australian clearinghouse network transferred most of the hardcopy collections to NCVER, to form a centralised repository of resources 2009 - materials produced by Reframing the Future (RTF) a vocational education and training workforce development initiative of the Australian, State and Territory Governments included in VOCED === 2009-2014 === A major rebuild of the database and website was undertaken during this period to take advantage of the potential of new technologies to provide improved services and incorporate Web 2.0 technologies (RSS feeds, and share and bookmark tools). 2009 - scope expanded to more fully encompass the higher education sector 2011 - launch of VOCEDplus with the name change representing the enhanced features and extended focus 2012 - a major retrospective digitisation project commenced and by the end of the 2012-2013 financial year a total of 9,328 publications (593,534 pages/microfiche frames) had been digitised, ensuring these publications are available electronically for free === 2014-2019 === A number of significant curated content products were released during this period. 2015 - release of a refreshed look to adopt the new NCVER branding plus a number of search enhancements (Guided search, Expert search, and Glossary search) were added 2015 - first in the series of 'Focus on...' pages released 2016 - launch of the 'Pod Network', a convenient and efficient platform that allows instant access to research and a multitude of resources on a range of subjects 2017 - completion of the 'Pod Network', consisting of 20 Pods (on broad subjects including Apprenticeships and traineeships, Foundation skills, Teaching and learning, Career development, and Students) and 74 Podlets (on narrow topics including Online learning, Social media, VET in schools, STEM skills, and Adult literacy) 2018 - launch of the 'Timeline of Australian VET Policy Initiatives' and the 'VET Knowledge Bank' which contains a suite of products capturing Australia's diverse, complex and ever-changing VET system 2019 - after an internal review, a refreshed, streamlined version of the 'Pod Network' was released, consisting of 13 Pods and 20 Podlets 2019 - launch of the 'VET Practitioner Resource' which contains a range of information to support VET practitioners in their work and is organised into three sections: (1) Teaching, training and assessment: standards, guidance, research and good practice resources to inform daily work; (2) Practitioners as researchers: information for undertaking practitioner-led research; and (3) The VET workforce: information about VET teachers and trainers, and the professional development needs of the VET workforce 2019 - VOCEDplus celebrated 30 years of providing information to the tertiary education sector and the homepage was refreshed to make it more modern and easier to use === 2020- === VOCEDplus continued to be accessible throughout the COVID-19 pandemic. 2020-2021 - the VET Knowledge Bank added a dedicated page, 'COVID-19 announcements', that showcases the measures introduced by the Australian, state and territory governments to mitigate the impact of the pandemic and promote economic recovery 2020-2024 - published research about the effects of the pandemic on education and training, providers, students, labour markets, employment and employees was collected and made permanently available in the database 2024 - VOCEDplus celebrated 35 years of providing information to the tertiary education sector. The homepage was refreshed and a number of enhancements and new features were implemented including a new My Profile feature, improvements to My Selection, accessible search history and saved searches, enhanced search functionality, and improved navigation.
Read more →
Repertory grid

The repertory grid is an interviewing technique which uses nonparametric factor analysis to determine an idiographic measure of personality. It was devised by George Kelly in around 1955 and is based on his personal construct theory of personality. == Introduction == The repertory grid is a technique for identifying the ways that a person construes (interprets or gives meaning to) his or her experience. It provides information from which inferences about personality can be made, but it is not a personality test in the conventional sense. It is underpinned by the personal construct theory developed by George Kelly, first published in 1955. A grid consists of four parts: A topic: it is about some part of the person's experience. A set of elements, which are examples or instances of the topic. Working as a clinical psychologist, Kelly was interested in how his clients construed people in the roles they adopted towards the client, and so, originally, such terms as "my father", "my mother", "an admired friend" and so forth were used. Since then, the grid has been used in much wider settings (educational, occupational, organisational) and so any well-defined set of words, phrases, or even brief behavioral vignettes can be used as elements. For example, to see how a person construes the purchase of a car, a list of vehicles within that person's price range could be a set of elements. A set of constructs. These are the basic terms that the client uses to make sense of the elements, and are always expressed as a contrast. Thus the meaning of "good" depends on whether you intend to say "good versus poor", as if you were construing a theatrical performance, or "good versus evil", as if you were construing the moral or ontological status of some more fundamental experience. A set of ratings of elements on constructs. Each element is positioned between the two extremes of the construct using a 5- or 7-point rating scale system; this is done repeatedly for all the constructs that apply; and thus its meaning to the client is modeled, and statistical analysis varying from simple counting, to more complex multivariate analysis of meaning, is made possible. Constructs are regarded as personal to the client, who is psychologically similar to other people depending on the extent to which they would tend to use similar constructs, and similar ratings, in relating to a particular set of elements. The client is asked to consider the elements three at a time, and to identify a way in which two of the elements might be seen as alike, but distinct from, contrasted to, the third. For example, in considering a set of people as part of a topic dealing with personal relationships, a client might say that the element "my father" and the element "my boss" are similar because they are both fairly tense individuals, whereas the element "my wife" is different because she is "relaxed". And so we identify one construct that the individual uses when thinking about people: whether they are "tense as distinct from relaxed". In practice, good grid interview technique would delve a little deeper and identify some more behaviorally explicit description of "tense versus relaxed". All the elements are rated on the construct, further triads of elements are compared and further constructs elicited, and the interview would continue until no further constructs are obtained. == Using the repertory grid == Careful interviewing to identify what the individual means by the words initially proposed, using a 5-point rating system could be used to characterize the way in which a group of fellow-employees are viewed on the construct "keen and committed versus energies elsewhere", a 1 indicating that the left pole of the construct applies ("keen and committed") and a 5 indicating that the right pole of the construct applies ("energies elsewhere"). On being asked to rate all of the elements, our interviewee might reply that Tom merits a 2 (fairly keen and committed), Mary a 1 (very keen and committed), and Peter a 5 (his energies are very much outside the place of employment). The remaining elements (another five people, for example) are then rated on this construct. Typically (and depending on the topic) people have a limited number of genuinely different constructs for any one topic: 6 to 16 are common when they talk about their job or their occupation, for example. The richness of people's meaning structures comes from the many different ways in which a limited number of constructs can be applied to individual elements. A person may indicate that Tom is fairly keen, very experienced, lacks social skills, is a good technical supervisor, can be trusted to follow complex instructions accurately, has no sense of humour, will always return a favour but only sometimes help his co-workers, while Mary is very keen, fairly experienced, has good social and technical supervisory skills, needs complex instructions explained to her, appreciates a joke, always returns favours, and is very helpful to her co-workers: these are two very different and complex pictures, using just 8 constructs about a person's co-workers. Important information can be obtained by including self-elements such as "Myself as I am now"; "Myself as I would like to be" among other elements, where the topic permits. == Analysis of results == A single grid can be analysed for both content (eyeball inspection) and structure (cluster analysis, principal component analysis, and a variety of structural indices relating to the complexity and range of the ratings being the chief techniques used). Sets of grids are dealt with using one or other of a variety of content analysis techniques. A range of associated techniques can be used to provide precise, operationally defined expressions of an interviewee's constructs, or a detailed expression of the interviewee's personal values, and all of these techniques are used in a collaborative way. The repertory grid is emphatically not a standardized "psychological test"; it is an exercise in the mutual negotiation of a person's meanings. The repertory grid has found favour among both academics and practitioners in a great variety of fields because it provides a way of describing people's construct systems (loosely, understanding people's perceptions) without prejudging the terms of reference—a kind of personalized grounded theory. Unlike a conventional rating-scale questionnaire, it is not the investigator but the interviewee who provides the constructs on which a topic is rated. Market researchers, trainers, teachers, guidance counsellors, new product developers, sports scientists, and knowledge capture specialists are among the users who find the technique (originally developed for use in clinical psychology) helpful. == Relationship to other tools == In the book Personal Construct Methodology, researchers Brian R. Gaines and Mildred L.G. Shaw noted that they "have also found concept mapping and semantic network tools to be complementary to repertory grid tools and generally use both in most studies" but that they "see less use of network representations in PCP [personal construct psychology] studies than is appropriate". They encouraged practitioners to use semantic network techniques in addition to the repertory grid.
Read more →
Innovation Center for Artificial Intelligence

The Innovation Center for Artificial Intelligence (ICAI) is a Dutch national network focused on joint technology development between academia, industry and government in the area of artificial intelligence (AI). The initiative was launched in April 2018 and is based at Amsterdam Science Park. As of 2024, the director of the ICAI is Maarten de Rijke. In November 2018, ICAI announced its contribution to AINED, the first iteration of the Dutch National AI Strategy. In January 2023, Maastricht University announced the ROBUST program, led by the Innovation Center for Artificial Intelligence (ICAI) and supported by the University of Amsterdam and others. This initiative focuses on advancing research in trustworthy AI technology across various sectors, notably healthcare and energy, in the Netherlands. The program's plan includes the creation of 17 new labs and the appointment of PhD candidates, backed by a €25 million funding from the Dutch Research Council (NWO). == Labs == The ICAI network is linked to several collaborative labs: Thira Lab (Imaging): Thirona, Delft Imaging Systems and Radboud UMC, founded March 2019 AIMLab (AI for Medical Imaging): Uva and Inception Institute of Artificial Intelligence from the United Arab Emirates, founded March 2019 AFL (AI for Fintech): ING and Delft University of Technology, founded March 2019 Police Lab AI: Dutch National Police, founded January 2019 Elsevier AI Lab: Uva and Elsevier, founded October 2018 AIRLab Delft (AI for Retail Robotics): TU Delft Robotics and AholdDelhaize, founded November 2018 Quva Lab (Deep Vision): Uva and Qualcomm, founded 2016 (prior to ICAI) AIRLab Amsterdam (AI for Retail): Uva and AholdDelhaize, founded April 2018 DeltaLab (Deep Learning Technologies Amsterdam): Uva and Bosch, founded April 2017 (prior to ICAI) AI4SE (AI for Software Engineering Lab) Delft University of Technology and JetBrains, founded October 2023 Atlas Lab: Uva and TomTom (TOM2)
Read more →
New Classification Scheme for Chinese Libraries

The New Classification Scheme for Chinese Libraries is a system of library classification developed by Lai Yung-hsiang since 1956. It is modified from "A System of Book Classification for Chinese Libraries" of Liu Guojun, which is based on the Dewey Decimal System. The scheme is developed for Chinese books and commonly used in Taiwan, Hong Kong and Macau. == Main classes == 000 Generalities 100 Philosophy 200 Religion 300 Sciences 400 Applied sciences 500 Social sciences 600 History of China and Geography of China 700 World history and Geography 800 Linguistics and Literature 900 Arts == Outline of the classification tables == 000 Generalities 000 Special collections 010 Bibliography; Literacy (Documentation) 020 Library and information science; Archive management 030 Sinology 040 General encyclopedia 050 Serial publications; Periodicals 060 General organization; Museology 070 General collected essays 080 General series 090 Collected Chinese classics 100 Philosophy 100 Philosophy: general 110 Thought; Learning 120 Chinese philosophy 130 Oriental philosophy 140 Western philosophy 150 Logic 160 Metaphysics 170 Psychology 180 Esthetics (Aesthetics) 190 Ethics 200 Religion 200 Religion: general 210 Science of religion 220 Buddhism 230 Taoism 240 Christianity 250 Islam (Mohammedanism) 260 Judaism 270 Other religions 280 Mythology 290 Astrology; Superstition 300 Sciences 300 Sciences: general 310 Mathematics 320 Astronomy 330 Physics 340 Chemistry 350 Earth science; Geology 360 Biological science 370 Botany 380 Zoology 390 Anthropology 400 Applied sciences 400 Applied sciences: general 410 Medical sciences 420 Home economics 430 Agriculture 440 Engineering 450 Mining and metallurgy 460 Chemical engineering 470 Manufacture 480 Commerce: various business 490 Commerce: administration and management 500 Social sciences 500 Social sciences: general 510 Statistics 520 Education 530 Rite and custom 540 Sociology 550 Economy 560 Finance 570 Political science 580 Law; Jurisprudence 590 Military science 600-700 History and geography 600 History and geography: General History and geography of China 610 General history of China 620 Chinese history by period 630 History of Chinese civilization 640 Diplomatic history of China 650 Historical sources 660 Geography of China 670 Local history 680 Topical topography 690 Chinese travels World history and geography 710 World: general history and geography 720 Oceans and seas 730 Asia: history and geography 740 Europe: history and geography 750 America: history and geography 760 Africa: history and geography 770 Oceania: history and geography 780 Biography 790 Antiquities and archaeology 800 Linguistics and literature 800 Linguistics: general 810 Literature: general 820 Chinese literature 830 Chinese literature: general collections 840 Chinese literature: individual works 850 Various Chinese literature 860 Oriental literature 870 Western literature 880 Other countries literatures 890 Journalism 900 Arts 900 Arts: general 910 Music 920 Architecture 930 Sculpture 940 Drawing and painting; Calligraphy 950 Photography; Computer art 960 Decorative arts 970 Arts and Crafts movement 980 Theatre 990 Recreation and leisure
Read more →
AI agent

In the context of generative artificial intelligence, AI agents (also referred to as compound AI systems or agentic AI) are a class of intelligent agents that can pursue goals, use tools, and take actions with varying degrees of autonomy. In practice, they usually operate within human-defined objectives, constraints, and available tools. == Overview == AI agents possess several key attributes, including goal-directed behavior, natural language interfaces, the capacity to use external tools, and the ability to perform multi-step tasks. Their control flow is frequently driven by large language models (LLMs). Agent systems may also include memory components, planning logic, tool interfaces, and orchestration software for coordinating agent components. AI agents do not have a standard definition. NIST describes agentic AI as an emerging area requiring standards for secure operation, interoperability, and reliable interaction with external systems. A common application of AI agents is task automation: for example, booking travel plans based on a user's prompted request. Companies such as Google, Microsoft and Amazon Web Services have offered platforms for deploying pre-built AI agents. Several protocols have been proposed for standardizing inter-agent communication, with examples including the Model Context Protocol, Gibberlink, and many others. Some of these protocols are also used for connecting agents to external applications. In December 2025, Linux Foundation announced the formation of the Agentic AI Foundation (AAIF), with the goal of ensuring agentic AI evolves transparently and collaboratively. == History == AI agents have been traced back to research from the 1990s, with Harvard professor Milind Tambe noting that the definition of an AI agent was not clear at the time. Researcher Andrew Ng has been credited with spreading the term "agentic" to a wider audience in 2024. == Training and testing == Researchers have attempted to build world models and reinforcement learning environments to train or evaluate AI agents. For example, video games such as Minecraft and No Man's Sky as well as replicas of company websites, have also been used for training such agents. == Autonomous capabilities == The Financial Times compared the autonomy of AI agents to the SAE classification of self-driving cars, likening most applications to level 2 or level 3, with some achieving level 4 in highly specialized circumstances, and level 5 being theoretical. == Cognitive architecture == The following are some internal design options for reasoning within an agent: Retrieval-augmented generation ReAct (Reason + Act) pattern is an iterative process in which an AI agent alternates between reasoning and taking actions, receives observations from the environment or external tools, and integrates these observations into subsequent reasoning steps. Reflexion, which uses an LLM to create feedback on the agent's plan of action and stores that feedback in a memory cache. A tool/agent registry, for organizing software functions or other agents that the agent can use. One-shot model querying, which queries the model once to create the plan of action. === Reference architecture === Ken Huang proposed an AI agent reference architecture, which consists of seven interconnected layers, with each layer building on the functionality of the layers beneath it: Layer 1: Foundation models - provide the core AI engines to power agent capabilities. Layer 2: Data operations - manage the complex data infrastructure required for AI agent operations, including Vector database, data loaders, RAG. Layer 3: Agent frameworks - sophisticated software and tools that simplify the development and management of the AI agents. Layer 4: Deployment and infrastructure - provide the robust technical foundation for running AI agents. Layer 5: Evaluation and observability - focus on assessing the safety and performance of AI agents. Layer 6: Security and compliance - a crucial protective framework ensuring AI agents operate safely, securely, and conform to regulatory boundaries. At this layer security and compliance features embedded into all the AI agent stack layers are integrated together. Layer 7: Agent ecosystem - represents the AI agents' interface with real-world applications and users. == Orchestration patterns == To execute complex tasks, autonomous agents are often integrated with other agents or specialized tools. These configurations, known as orchestration patterns or workflows, include the following: Prompt chaining: A sequence where the output of one step serves as the input for the next. Routing: The classification of an input to direct it to a specialized downstream task or tool. Parallelization: The simultaneous execution of multiple tasks. Sequential processing: A fixed, linear progression of tasks through a predefined pipeline. Planner-critic: An iterative pattern where one agent generates a proposal and another evaluates it to provide feedback for refinement. == Multimodal AI agents == In addition to large language models (LLMs), vision-language models (VLMs) and multimodal foundation models can be used as the basis for agents. In September 2024, Allen Institute for AI released an open-source vision-language model. Nvidia released a framework for developers to use VLMs, LLMs and retrieval-augmented generation for building AI agents that can analyze images and videos, including video search and video summarization. Microsoft released a multimodal agent model – trained on images, video, software user interface interactions, and robotics data – that the company claimed can manipulate software and robots. == Applications == As of April 2025, per the Associated Press, there are few real-world applications of AI agents. As of June 2025, per Fortune, many companies are primarily experimenting with AI agents. The Information divided AI agents into seven archetypes: business-task agents, for acting within enterprise software; conversational agents, which act as chatbots for customer support; research agents, for querying and analyzing information (such as OpenAI Deep Research); analytics agents, for analyzing data to create reports; software developer or coding agents (such as Cursor); domain-specific agents, which include specific subject matter knowledge; and web browser agents (such as OpenAI Operator). By mid-2025, AI agents have been used in video game development, gambling (including sports betting), cryptocurrency wallets (including cryptocurrency trading and meme coins) and social media. In August 2025, New York Magazine described software development as the most definitive use case of AI agents. Likewise, by October 2025, noting a decline in expectations, The Information noted AI coding agents and customer support as the primary use cases by businesses. In November 2025, The Wall Street Journal reported that few companies that deployed AI agents have received a return on investment. === Applications in government === Several government bodies in the United States and United Kingdom have deployed or announced the deployment of agents, at the local and national level. The city of Kyle, Texas deployed an AI agent from Salesforce in March 2025 for 311 customer service. In November 2025, the Internal Revenue Service stated that it would use Agentforce, AI agents from Salesforce, for the Office of Chief Counsel, Taxpayer Advocate Services and the Office of Appeals. That same month, Staffordshire Police announced that they would trial Agentforce agents for handling non-emergency 101 calls in the United Kingdom starting in 2026. In December 2025, the Department of Neighborhoods in Detroit, Michigan, in partnership with a local business, deployed a pilot project in two Detroit districts for an AI agent to be used for customer service calls. In February 2025, Thomas Shedd, the director of the Technology Transformation Services, proposed using AI coding agents across the United States federal government. A recruiter for the Department of Government Efficiency proposed in April 2025 to use AI agents to automate the work of about 70,000 United States federal government employees, as part of a startup with funding from OpenAI and a partnership agreement with Palantir. This proposal was criticized by experts for its impracticality, if not impossibility, and the lack of corresponding widespread adoption by businesses. In December 2025, the Food and Drug Administration announced that it would offer "agentic AI capabilities" to its staff for "meeting management, pre-market reviews, review validation, post-market surveillance, inspections and compliance and administrative functions." That same month, the United States Department of Defense launched GenAI.mil, an internal platform for American military personnel to use generative AI-based applications based on Google Gemini, including "intelligent agentic workflows". Defense Secretary Pete Hegseth listed applications such as "[conducting] deep r
Read more →
Hive (artificial intelligence company)

Hive is an American artificial intelligence company offering machine learning models via APIs to enterprise customers. Hive uses around 700,000 gig workers to train data for its models through its Hive Work app. One of Hive's major offerings is to provide automated content moderation services. == Products == Hive is reported to have been engaged to provide content moderation services to social news aggregator Reddit, Giphy, BeReal, Donald Trump-affiliated social network Truth Social, and on online chat website Chatroulette. Parler, after its shutdown by content service providers in early 2021 due to a lack of content moderation, integrated with Hive and was allowed back in the App Store. Hive's content moderation models have been leveraged widely in the livestreaming industry, where the cost of human moderation is high. Hive's models have also been used in events such as the Super Bowl and March Madness, and its contextual advertising models used by NBC Universal and Vevo. Hive provides APIs to detect deepfakes and AI-generated artwork. In early 2023, Hive released a free demo text classifier intended to detect AI-generated text. Mark Hachman at PC World rated Hive's classifier favorably and found it more reliable than OpenAI's AI text classifier. == History == Hive was founded by Kevin Guo and Dmitriy Karpman, and in April 2021, announced $85M in new capital at a valuation of $2 billion.
Read more →
AI-assisted virtualization software

AI-assisted virtualization software is a type of technology that combines the principles of virtualization with advanced artificial intelligence (AI) algorithms. This software is designed to improve efficiency and management of virtual environments and resources. This technology has been used in cloud computing and for various industries. == History == Virtualization originated in mainframe computers in the 1960s in order to divide system resources between different applications. The term has since broadened. The use of AI in virtualization significantly increased in the early 2020s. == Uses == AI-assisted virtualization software uses AI-related technology such as machine learning, deep learning, and neural networks to attempt to make more accurate predictions and decisions regarding the management of virtual environments. Features include intelligent automation, predictive analytics, and dynamic resource allocation. Intelligent Automation: Automating tasks such as resource provisioning and routine maintenance. The AI learns from ongoing operations and can predict and perform necessary tasks autonomously. Predictive Analytics: Utilizing AI to analyze data patterns and trends, predicting future issues or resource requirements. It aids in proactive management and mitigation of potential problems. Dynamic Resource Allocation: Through the analysis of real-time and historical data, the AI system dynamically assigns resources based on demand and need, optimizing overall system performance and reducing wastage. AI-assisted virtualization software has been used in cloud computing to optimize the use of resources and reduce costs. In healthcare, these technologies have been used to create virtual patient profiles. They are also used in data centers to improve performance and energy efficiency. It has also been used in network function virtualization (NFV) to improve virtual network infrastructure. Implementing this type of software requires a high degree of technological sophistication and can incur significant costs. There are also concerns about the risks associated with AI, such as algorithmic bias and security vulnerabilities. Additionally, there are issues related to governance, the ethics of artificial intelligence, and regulations of AI technologies.
Read more →
SHRDLU

SHRDLU is an early natural-language understanding computer program that was developed by Terry Winograd at MIT in 1968–1970. In the program, the user carries on a conversation with the computer, moving objects, naming collections and querying the state of a simplified "blocks world", essentially a virtual box filled with different blocks. SHRDLU was written in the Micro Planner and Lisp programming language on the DEC PDP-6 computer and a DEC graphics terminal. Later additions were made at the computer graphics labs at the University of Utah, adding a full 3D rendering of SHRDLU's "world". The name SHRDLU was derived from ETAOIN SHRDLU, the arrangement of the letter keys on a Linotype machine, arranged in descending order of usage frequency in English. == Functionality == SHRDLU is primarily a language parser that allows user interaction using English terms. The user instructs SHRDLU to move various objects around in the "blocks world" containing various basic objects such as blocks, cones and balls. SHRDLU combined four simple ideas to make the simulation of "understanding" more convincing. One was that SHRDLU's world is so simple that the entire set of objects and locations could be described by including as few as 50 words: nouns like "block" and "cone", verbs like "place on" and "move to", and adjectives like "big" and "blue". The possible combinations of these basic language building blocks are quite simple. SHRDLU also includes a basic memory to supply context. One could ask SHRDLU to "put the green cone on the red block" and then "take the cone off"; "the cone" would be taken to mean the green cone one had just talked about. SHRDLU can search back further through the interactions to find the proper context in most cases when additional adjectives were supplied. One could also ask questions about the history; for instance, one could ask "did you pick up anything before the cone?" A side effect of this memory, and the original rules SHRDLU was supplied with, is that the program can answer questions about what was possible in the world and what was not. For instance, SHRDLU can deduce that blocks could be stacked by looking for examples, but also realize that triangles could not be stacked, after having tried it. The "world" contains basic physics to make blocks fall over, independent of the language parser. Finally, SHRDLU can also remember names given to objects, or arrangements of them. For instance one could say "a steeple is a small triangle on top of a tall rectangle"; SHRDLU can then answer questions about steeples in the blocks world, and build new ones. This is an example of a SHRDLU session: Person: Pick up a big red block. Computer: OK. Person: Grasp the pyramid. Computer: I DON'T UNDERSTAND WHICH PYRAMID YOU MEAN. Person (changing their mind): Find a block which is taller than the one you are holding and put it into the box. Computer: BY "IT", I ASSUME YOU MEAN THE BLOCK WHICH IS TALLER THAN THE ONE I AM HOLDING. Computer: OK. Person: What does the box contain? Computer: THE BLUE PYRAMID AND THE BLUE BLOCK. Person: What is the pyramid supported by? Computer: THE BOX. Person: How many blocks are not in the box? Computer: FOUR OF THEM. Person: Is at least one of them narrower than the one which i told you to pick up? Computer: YES, THE RED CUBE. Person: Is it supported? Computer: YES, BY THE TABLE. Person: Can the table pick up blocks? Computer: NO. Person: Can a pyramid be supported by a block? Computer: YES. Person: Can a pyramid support a pyramid? Computer: I DON'T KNOW. Person: Stack up two pyramids. Computer: I CAN'T. Person: Will you please stack up both of the red blocks and either a green cube or a pyramid? Computer: OK. Person: Which cube is sitting on the table? Computer: THE LARGE GREEN ONE WHICH SUPPORTS THE RED PYRAMID. Person: Is there a large block behind a pyramid? Computer: YES, THREE OF THEM: A LARGE RED ONE, A LARGE GREEN CUBE, AND THE BLUE ONE. Person: Put a small one onto the green cube which supports a pyramid. Computer: OK. Person: Put the littlest pyramid on top of it. Computer: OK. Person: Does the shortest thing the tallest pyramid's support supports support anything green? Computer: YES, THE GREEN PYRAMID. Person: What color is it? Computer: BY "IT", I ASSUME YOU MEAN THE SHORTEST THING THE TALLEST PYRAMID'S SUPPORT SUPPORTS. Computer: RED Person: How many things are on top of green cubes? Computer: I'M NOT SURE WHAT YOU MEAN BY "ON TOP OF" IN THE PHRASE "ON TOP OF GREEN CUBES" . DO YOU MEAN: 1 - DIRECTLY ON THE SURFACE 2 - ANWHERE ON TOP OF ? Person: 2 Computer: THREE OF THEM. Person: Had you touched any pyramid before you put the green one on the little cube? Computer: YES, THE GREEN ONE. Person: When did you pick it up? Computer: WHILE I WAS STACKING UP THE RED CUBE, A LARGE RED BLOCK AND A LARGE GREEN CUBE. Person: Why? Computer: TO GET RID OF IT. Person: Why did you do that? Computer: TO CLEAN OFF THE RED CUBE. Person: Why did you clear off that cube? Computer: TO PUT IT ON A LARGE GREEN CUBE. Person: Why did you do that? Computer: TO STACK UP THE RED CUBE , A LARGE RED BLOCK AND A LARGE GREEN CUBE. Person: Why did you do that? Computer: BECAUSE YOU ASKED ME TO. Person: How did you do it? Computer: BY PUTTING A LARGE RED BLOCK ON THE TABLE ; THEN LETTING GO OF IT ; THEN PUTTING A LARGE GREEN CUBE ON IT ; THEN LETTING GO OF THAT CUBE ; THEN PUTTING THE RED CUBE ON THAT CUBE; THEN LETTING GO OF THAT CUBE. Person: How many objects did you touch while you were doing it? Computer: FOUR OF THEM. Person: What did the red cube support before you started to clean it off? Computer: THE GREEN PYRAMID. Person: There were five blocks to the left of the box then. Computer: NO, ONLY FOUR OF THEM: THE RED CUBE, TWO LARGE GREEN CUBES AND A LARGE RED BLOCK. Person: Put the blue pyramid on the block in the box. Computer: OK. Person: Is there anything which is bigger than every pyramid but is not as wide as the thing that supports it? Computer: YES, THE BLUE BLOCK. Person: Does a steeple Computer (interrupting): SORRY, I DON'T KNOW THE WORD "STEEPLE". Person: A "steeple" is a stack which contains two green cubes and a pyramid. Computer: I UNDERSTAND. Person: Are there any steeples now? Computer: NO. Person: Build one. Computer: OK. Person: Call the biggest block "superblock". Computer: OK. Person: Have you picked superblock up since we began? Computer: YES. Person: Why did you drop it? Computer: BY "IT", I ASSUME YOU MEAN THE SUPERBLOCK. I CAN'T EXPLAIN A NON-EXISTENT EVENT. Person: Is there anything to the right of the red pyramid? Computer: YES, FOUR THINGS: THE BOX, THE RED CUBE, THE BLUE PYRAMID AND THE BLOCK NAMED SUPERBLOCK Person: Thank you. Computer: YOU'RE WELCOME! == Consequences == SHRDLU was considered a tremendously successful demonstration of artificial intelligence (AI). This led other AI researchers to excessive optimism which was soon lost when later systems attempted to deal with situations with a more realistic level of ambiguity and complexity. Subsequent efforts of the SHRDLU type, such as Cyc, have tended to focus on providing the program with considerably more information from which it can draw conclusions. In a 1991 interview, Winograd said about SHRDLU: [...] the famous dialogue with SHRDLU where you could pick up a block, and so on, I very carefully worked through, line by line. If you sat down in front of it, and asked it a question that wasn't in the dialogue, there was some probability it would answer it. I mean, if it was reasonably close to one of the questions that was there in form and in content, it would probably get it. But there was no attempt to get it to the point where you could actually hand it to somebody and they could use it to move blocks around. And there was no pressure for that whatsoever. Pressure was for something you could demo. Take a recent example, Negroponte's Media Lab, where instead of "perish or publish" it's "demo or die." I think that's a problem. I think AI suffered from that a lot, because it led to "Potemkin villages", things which - for the things they actually did in the demo looked good, but when you looked behind that there wasn't enough structure to make it really work more generally. Though not intentionally developed as such, SHRDLU is considered the first known formal example of interactive fiction, as the user interacts with simple commands to move objects around a virtual environment, though lacking the distinct story-telling normally present in the interactive fiction genre. The 1976-1977 game Colossal Cave Adventure is broadly considered to be the first true work of interactive fiction.
Read more →
SlideRocket

SlideRocket was an online presentation platform that let users create, manage, share and measure presentations. SlideRocket was provided via a SaaS model. The company was acquired by VMware in April 2011, who sold it to ClearSlide, a similar SaaS application, in March 2013. It is no longer offering independent signups, as the platform is being integrated into ClearSlide. == History == SlideRocket was founded in Jan 2006, and launched as a private beta in March 2008 at the Under The Radar Spring event. A public beta was announced in September 2008 followed shortly by public release on October 28, 2008. SlideRocket is most commonly credited with inventing the PResuMÉ or Presentation Résumé in early 2009. On April 26, 2011, SlideRocket was acquired by VMware. On March 5, 2013, VMware sold SlideRocket to ClearSlide. SlideRocket is based in San Francisco.
Read more →
LIFER/LADDER

LIFER/LADDER was one of the first database natural language processing systems. It was designed as a natural language interface to a database of information about US Navy ships. This system, as described in a paper by Hendrix (1978), used a semantic grammar to parse questions and query a distributed database. It was implemented in Interlisp. The LIFER/LADDER system could only support simple one-table queries or multiple table queries with easy join conditions. Some examples of queries it could accept: What are the length, width, and draft of the Kitty Hawk? When will Reeves achieve readiness rating C2? What is the nearest ship to Naples with a doctor on board? What ships are carrying cargo for the United States? Where are they going? Print the American cruisers’ current positions and states of readiness?
Read more →
Mycin

MYCIN was an early backward chaining expert system that used black box to identify bacteria causing severe infections, such as bacteremia and meningitis, and to recommend antibiotics, with the dosage adjusted for patient's body weight — the name derived from the antibiotics themselves, as many antibiotics have the suffix "-mycin". The Mycin system was also used for the diagnosis of blood clotting diseases. MYCIN was developed over five or six years in the early 1970s at Stanford University. It was written in Lisp as the doctoral dissertation of Edward Shortliffe under the direction of Bruce G. Buchanan, Stanley N. Cohen and others. MYCIN emerged from the Stanford Heuristic Programming Project. MYCIN demonstrated the potential for expert systems in building high-performance medical reasoning programs. MYCIN is often viewed as a pioneer in the field of expert systems, even being referred to as the "grandaddy of them all-the one that launched the field" by Dr. Allen Newell. MYCIN led to the EMYCIN expert system shell ("essential MYCIN") for acquiring knowledge, reasoning with it, and explaining the results, without the specific medical knowledge. It can be described as "EMYCIN = Prolog + uncertainty + caching + questions + explanations + contexts - variables". An introduction is in Chapter 16 of Paradigms of Artificial Intelligence Programming (PAIP). == Method == MYCIN operated using a fairly simple inference engine and a knowledge base of ~600 rules by obtaining individual inferential facts identified by experts and encoding such facts as individual production rules. No other AI program at the time contained as much domain-specific knowledge clearly separated from its inference procedures as MYCIN. It would query the physician running the program via a long series of simple yes/no or textual questions. At the end, it provided a list of possible culprit bacteria ranked from high to low based on the probability of each diagnosis, its confidence in each diagnosis' probability, the reasoning behind each diagnosis (that is, MYCIN would also list the questions and rules which led it to rank a diagnosis a particular way), and its recommended course of drug treatment. MYCIN could additionally respond to queries by physicians related to why it asked the user a certain question, how it arrived at a conclusion, and why it did not consider certain factors. The developers performed studies showing that MYCIN's performance was minimally affected by perturbations in the uncertainty metrics associated with individual rules, suggesting that the power in the system was related more to its knowledge representation and reasoning scheme than to the details of its numerical uncertainty model. Some observers felt that it should have been possible to use classical Bayesian statistics. MYCIN's developers argued that this would require either unrealistic assumptions of probabilistic independence, or require the experts to provide estimates for an unfeasibly large number of conditional probabilities. Subsequent studies later showed that the certainty factor model could indeed be interpreted in a probabilistic sense, and highlighted problems with the implied assumptions of such a model. However the modular structure of the system would prove very successful, leading to the development of graphical models such as Bayesian networks. === Context === A context in MYCIN determines what types of objects can be reasoned about. They are similar to variables in Prolog, or environment variables in operating systems. === Evidence combination === In MYCIN it was possible that two or more rules might draw conclusions about a parameter with different weights of evidence. For example, one rule may conclude that the organism in question is E. Coli with a certainty of 0.8 whilst another concludes that it is E. Coli with a certainty of 0.5 or even −0.8. In the event the certainty is less than zero the evidence is actually against the hypothesis. In order to calculate the certainty factor MYCIN combined these weights using the formula below to yield a single certainty factor: C F ( x , y ) = { X + Y − X Y if X , Y > 0 X + Y + X Y if X , Y < 0 X + Y 1 − min ( | X | , | Y | ) otherwise {\displaystyle CF(x,y)={\begin{cases}X+Y-XY&{\text{if }}X,Y>0\\X+Y+XY&{\text{if }}X,Y<0\\{\frac {X+Y}{1-\min(|X|,|Y|)}}&{\text{otherwise}}\end{cases}}} Where X and Y are the certainty factors. This formula can be applied more than once if more than two rules draw conclusions about the same parameter. It is commutative, so it does not matter in which order the weights were combined. The combination formula was designed to have the following desirable properties: −1 can be interpreted as "false", +1 as "true", and 0 as "uncertain". Combining unknown with anything leaves it unchanged. Combining true with anything (except false) gives true. Similarly for false. Combining true and false is a division-by-zero error. Combining +x and -x gives unknown. Combining two positives (except true) gives a larger positive. Similarly for negatives. Combining a positive and a negative gives something in between. === Examples === The following examples come from Chapter 16 of PAIP, which contains an implementation in Common Lisp of a modified and simplified version of MYCIN for pedagogical purposes. A rule, and an English paraphrase generated by the system: == Results == An evaluation of MYCIN was conducted at the Stanford Medical School. The first phase of the evaluation consisted of 10 test cases of diverse origin, chosen by a physician who was not acquainted with MYCIN's methods or knowledge base. These cases were presented to 7 physicians and 1 senior medical student. 10 prescriptions were compiled for each of the cases, 1 recommended by MYCIN, 1 prescribed by the treating physician at the county hospital, and 8 by the aforementioned individuals. The second phase of the evaluation consisted of eight infectious disease specialists being provided the clinical summary and set of 10 prescriptions for each of the 10 cases and tasked to provide their own recommendations for each case and assess the 10 prescriptions. MYCIN received an acceptability rating of 65%, which was comparable to the 42.5% to 62.5% rating of five faculty members. This study is often cited as showing the potential for disagreement about therapeutic decisions, even among experts, when there is no "gold standard" for correct treatment. == Practical use == MYCIN was never actually used in practice. This wasn't because of any weakness in its performance. Some observers raised ethical and legal issues related to the use of computers in medicine, regarding the responsibility of the physicians in case the system gave wrong diagnosis. However, the greatest problem, and the reason that MYCIN was not used in routine practice, was the state of technologies for system integration, especially at the time it was developed. MYCIN was a stand-alone system that required a user to enter all relevant information about a patient by typing in responses to questions MYCIN posed. MYCIN ran on the DEC KI10 PDP-10, supporting a large time-shared system available over the early Internet (ARPANet), before personal computers were developed. MYCIN's greatest influence was accordingly its demonstration of the power of its representation and reasoning approach. Rule-based systems in many non-medical domains were developed in the years that followed MYCIN's introduction of the approach. In the 1980s, expert system "shells" were introduced (including one based on MYCIN, known as E-MYCIN (followed by Knowledge Engineering Environment - KEE)) and supported the development of expert systems in a wide variety of application areas. A difficulty that rose to prominence during the development of MYCIN and subsequent complex expert systems has been the extraction of the necessary knowledge for the inference engine to use from the human expert in the relevant fields into the rule base (the so-called "knowledge acquisition bottleneck").
Read more →