VK (short for its original name VKontakte; Russian: ВКонтакте, lit. 'InContact') is a Russian online social media and social networking service based in Saint Petersburg. VK is available in multiple languages but it is predominantly used by Russian speakers. VK users can message each other publicly or privately, edit messages, create groups, public pages, and events; share and tag images, audio, and video; and play browser-based games. As of August 2018, VK had at least 500 million accounts. As of November 2022, it was the sixth most popular website in Russia. The network was also popular in Ukraine until it was banned by the Verkhovna Rada in 2017. According to Semrush, in 2024, VK was the 30th most visited website in the world; as YouTube is subject to blocking in Russia, VK Video overtook Google's top position in monthly web traffic for the first time in December 2024, as part of the major substitution to domestic business. == History == VKontakte was conceived in 2006 when Pavel Durov, creator of the popular student forum spbgu.ru, met his former classmate Vyacheslav Mirilashvili in St. Petersburg after graduating from the Faculty of Philology at St Petersburg State University. Vyacheslav showed Durov the increasingly popular Facebook, after which the friends decided to create a new Russian social network. Lev Leviev, an Israeli classmate of Vyacheslav Mirilashivili, became the third co-founder. Vyacheslav Mirilashvili borrowed the money from his billionaire father and became the largest shareholder. Lev Leviev took over operational management, and Durov became CEO. Pavel Durov convinced his older brother Nikolai, a multiple winner of international math and programming competitions, to develop the site. Durov launched VKontakte for beta testing in September 2006. The following month, the domain name Vkontakte.ru was registered. The new project was incorporated on 19 January 2007 as a Russian private limited company. In February 2007 the site reached a user base of over 100,000 and was recognized as the second largest company in Russia's nascent social network market. In the same month, the site was subjected to a severe DDoS attack, which briefly put it offline. The user base reached 1 million in July 2007, and 10 million in April 2008. In December 2008 VK overtook rival Odnoklassniki as Russia's most popular social networking service. == Website == Similar to many social networks, the platform's fundamental features revolve around private messaging, sharing photos, posting status updates, and exchanging links with friends. VK also provides tools for administering online communities and managing celebrity pages. The site allows its users to upload, search and stream media content, such as videos and music. VK features an advanced search engine, that allows complex queries for finding friends, as well as a real-time news search. VK updated its features and design in April 2016. === Features === Messaging. VK Private Messages can be exchanged between groups of 2 to 500 people. An email address can also be specified as the recipient. Each message may contain up to 10 attachments: Photos, Videos, Audio Files, Maps (an embedded map with a manually placed marker), and Documents. News. VK users can post on their profile walls, each post may contain up to 10 attachments – media files, maps, and documents (see above). User mentions and hashtags are supported. In the case of multiple photo attachments, the previews are automatically scaled and arranged in a magazine-style layout. The news feed can be switched between all news (default) and most interesting modes. The site features a news-recommendation engine, global real-time search, and individual search for posts and comments on specific users' walls. Communities. VK features three types of communities. Groups are better suited for decentralized communities (discussion boards, wiki-style articles, editable by all members, etc.). Public pages is a news feed-orientated broadcasting tool for celebrities and businesses. The two types are largely interchangeable, the main difference being in the default settings. The third type of community is called Events, which are used for appropriately organizing concerts and events in an appropriate way. Like buttons. VK like buttons for posts, comments, media, and external sites operate differently from Facebook. Liked content doesn't get automatically pushed to the user's wall, but is saved in the private Favorites section instead. The user has to press a second 'share with friends' button to share an item on their wall or send it via private message to a friend. Privacy. Users can control the availability of their content within the network and on the Internet. Blanket and granular privacy settings are available for pages and individual content. Synchronization with other social networks. Any news published on the VK wall will appear on Facebook or Twitter. Certain news may not be published by clicking on the logo next to the "Send" button. Editing a post in VK does not change the post in Facebook or Twitter and vice versa. However, removing the news in VK will remove it from other social networks. SMS service. Russian users can receive and reply to a private message or leave a comment for community news using SMS. Music. Users have access to the audio files uploaded by other users. In addition, users can upload the audio files themselves, create playlists and share audios with others by attaching to messages and wall posts. The uploaded audio files cannot violate copyright laws. === Popularity === As of May 2017, according to Alexa Internet ranking, VK is one of the most visited websites in some Eurasian countries. It is: 4th most visited in Russia; 3rd most visited in Belarus; 6th most visited in Kazakhstan; 8th most visited in Kyrgyzstan and Moldova; 12th most visited in Latvia. It was the fourth most viewed site in Ukraine until, in May 2017, the Ukrainian government banned the use of VK in Ukraine. According to a study for May 2018 conducted by Factum Group Ukraine VK remained the fourth most viewed site in Ukraine, but Facebook was twice as much visited. For 2019, VK appeared as the most visited social network in Ukraine according to Alexa. According to the Internet Association of Ukraine the share of Ukrainian Internet users who visit VK daily had fallen from 54% to 10% from September 2016 to September 2019. They also claimed in November 2019 that Facebook was the most popular social network. VK was expected to gain most of the users lost by Facebook and Instagram after they were blocked in Russia in 2022, according to a Calltouch poll. == Ownership == Initially, founder and CEO Pavel Durov owned 20% of shares (although he had majority voting power through proxy votes), and a trio of Russian-Israeli investors Yitzchak Mirilashvili, his father Mikhael Mirilashvili, and Lev Leviev owned 60%, 10%, and 10% respectively. In 2007, Digital Sky Technologies, an investment company managed by Yuri Milner, acquired a total of 24.99% of the shares from shareholders, investing $16.3 million. In preparation for the IPO in September 2010, DST separated international and Russian assets: the former formed the DST Global fund, while the latter, including VKontakte and rival social network Odnoklassniki, were merged into Mail.ru Group. Mail.ru Group used part of the money to acquire 7.5% of the social network for $112.5 million at a valuation of the entire project of 1.5 billion dollars. After exercising a 7.5% option in July 2011 for $111.7 million, Mail.ru Group accumulated a 39.99% stake in VKontakte. The head of Mail.ru Group, Dmitry Grishin, voiced the company's intention to gain 100% control over VKontakte. MRG was discussing with shareholders to buy out shares from the valuation of the entire company in $2-3 billion. In the summer of 2011, Mirilashvili and Leviev were ready to accept in payment owned by Mail.ru Group shares of Facebook, Groupon, and Zynga, but the deal failed due to Durov's unwillingness to sell a stake on MRG terms. Later, the co-founders considered VKontakte's IPO as an alternative. In March 2012, Durov "accidentally" became plugged into the negotiations where Mirilashvili and Leviev discussed selling their stakes directly to Mail.ru Group's main investor, Alisher Usmanov. On the same day, Durov deleted the pages of the first co-investors, stopped contacting them, and soon announced that VKontakte would postpone its IPO indefinitely. On 29 May 2012, Mail.ru Group announced its decision to yield control of the company to Durov by offering him the voting rights on its shares. Combined with Durov's personal 12% stake, this gave him 52% of the votes. In April 2013, the Mirilashvili family sold its 40% share in VK to United Capital Partners for $1.12 billion, while Lev Leviev sold his 8% share in the same deal, giving United Capital Partners 48% ownership. In January 2014, VK's founder Pavel Durov sold his 12% stake in the company to I
Chatbot
A chatbot (originally chatterbot) is a software application or web interface designed to converse through text or speech. Modern chatbots are typically online and use generative artificial intelligence systems that are capable of maintaining a conversation with a user in natural language and simulating the way a human would behave as a conversational partner. Such chatbots often use deep learning and natural language processing. Simpler chatbots have existed for decades. Chatbots have gained popularity during the AI boom of the 2020s, with the releases of generative AI chatbots such as ChatGPT, Gemini, Claude, and Grok. These chatbots typically use fine-tuned large language models to generate text. A major area where chatbots have long been used is customer service and support, with various sorts of virtual assistants. == History == === Turing test === In 1950, Alan Turing published an article entitled "Computing Machinery and Intelligence" in which he proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, to the extent that the judge is incapable of reliably distinguishing, on the basis of the conversational content alone, between the program and a real human. === Early chatbots === Joseph Weizenbaum's program ELIZA was first published in 1966. Weizenbaum did not claim that ELIZA was genuinely intelligent, and the introduction to his paper presented it more as a debunking exercise:In artificial intelligence, machines are made to behave in wondrous ways, often sufficient to dazzle even the most experienced observer. But once a particular program is unmasked, once its inner workings are explained, its magic crumbles away; it stands revealed as a mere collection of procedures. The observer says to himself "I could have written that". With that thought, he moves the program in question from the shelf marked "intelligent", to that reserved for curios. The object of this paper is to cause just such a re-evaluation of the program about to be "explained". Few programs ever needed it more. ELIZA's key method of operation involves the recognition of clue words or phrases in the input, and the output of the corresponding pre-prepared or pre-programmed responses that can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word 'MOTHER' with 'TELL ME MORE ABOUT YOUR FAMILY'). Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate because human judges are ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent". Following ELIZA, psychiatrist Kenneth Colby developed PARRY in 1972. From 1978 to some time after 1983, the CYRUS project led by Janet Kolodner constructed a chatbot simulating Cyrus Vance (57th United States Secretary of State). It used case-based reasoning, and updated its database daily by parsing wire news from United Press International. The program was unable to process the news items subsequent to the surprise resignation of Cyrus Vance in April 1980, and the team constructed another chatbot simulating his successor, Edmund Muskie. In 1984, an interactive version of the program Racter was released which acted as a chatbot. A.L.I.C.E. was released in 1995. This uses a markup language called AIML, which is specific to its function as a conversational agent, and has since been adopted by various other developers of, so-called, Alicebots. A.L.I.C.E. is a weak AI without any reasoning capabilities. It is based on a similar pattern matching technique as ELIZA in 1966. This is not strong AI, which would require sapience and logical reasoning abilities. Jabberwacky, released in 1997, learns new responses and context based on real-time user interactions, rather than being driven from a static database. Chatbot competitions focus on the Turing test or more specific goals. Two such annual contests are the Loebner Prize and The Chatterbox Challenge (the latter has been offline since 2015, however, materials can still be found from web archives). Pre-dating the current generation of large language models, Gavagai, a Swedish language technology startup, created a Twitter-based bot in 2015 and DBpedia created a chatbot during the 2017 Google Summer of Code that communicated through Facebook Messenger. === Modern chatbots based on large language models === Modern chatbots like ChatGPT are often based on foundational large language models called generative pre-trained transformers (GPT). They are based on a deep learning architecture called the transformer, which contains artificial neural networks. They generate text after being trained on a large text corpus, and have emergent abilities that they are not specifically trained for. Chatbots integrated into apps and websites can call image-generation models or search the web. Some platforms also enable users to interact with conversational interfaces directly through web-based chat environments, allowing real-time assistance, content generation, and task automation without requiring software installation. == Application == === Messaging apps === Many companies' chatbots run on messaging apps or simply via SMS. They are used for B2C customer service, sales and marketing. In 2016, Facebook Messenger allowed developers to place chatbots on their platform. There were 30,000 bots created for Messenger in the first six months, rising to 100,000 by September 2017. Since September 2017, this has also been as part of a pilot program on WhatsApp. Airlines KLM and Aeroméxico both announced their participation in the testing; both airlines had previously launched customer services on the Facebook Messenger platform. The bots usually appear as one of the user's contacts, but can sometimes act as participants in a group chat. Many banks, insurers, media companies, e-commerce companies, airlines, hotel chains, retailers, health care providers, government entities, and restaurant chains have used chatbots to answer simple questions, increase customer engagement, for promotion, and to offer additional ways to order from them. Chatbots are also used in market research to collect short survey responses. A 2017 study showed 4% of companies used chatbots. In a 2016 study, 80% of businesses said they intended to have one by 2020. ==== As part of company apps and websites ==== Previous generations of chatbots were present on company websites, e.g. Ask Jenn from Alaska Airlines which debuted in 2008 or Expedia's virtual customer service agent which launched in 2011. The newer generation of chatbots includes IBM Watson-powered "Rocky", introduced in February 2017 by the New York City-based e-commerce company Rare Carat to provide information to prospective diamond buyers. ==== Chatbot sequences ==== Used by marketers to script sequences of messages, very similar to an autoresponder sequence. Such sequences can be triggered by user opt-in or the use of keywords within user interactions. After a trigger occurs a sequence of messages is delivered until the next anticipated user response. Each user response is used in the decision tree to help the chatbot navigate the response sequences to deliver the correct response message. === Company internal platforms === Companies have used chatbots for customer support, human resources, or in Internet-of-Things (IoT) projects. Overstock.com, for one, has reportedly launched a chatbot named Mila to attempt to automate certain processes when customer service employees request sick leave. Other large companies such as Lloyds Banking Group, Royal Bank of Scotland, Renault and Citroën are now using chatbots instead of call centres with humans to provide a first point of contact. In large companies, like in hospitals and aviation organizations, chatbots are also used to share information within organizations, and to assist and replace service desks. === Customer service === Chatbots have been proposed as a replacement for customer service departments. In 2026, The Financial Times reported on agentic chatbots that could do shopping for customers once given instructions. In 2016, Russia-based Tochka Bank launched a chatbot on Facebook for a range of financial services, including a possibility of making payments. In July 2016, Barclays Africa also launched a Facebook chatbot. === Healthcare === Chatbots are also appearing in the healthcare industry. A study suggested that physicians in the United States believed that chatbots would be most beneficial for scheduling doctor appointments, locating health clinics, or providing medication information. A 2025 review found that participants often rated chatbot responses as more empathic than those from clinicians. In 2020, WhatsApp worked with th
Library classification
A library classification is a system used within a library to organize materials, including books, sound and video recordings, electronic materials, etc., both on shelves and in catalogs and indexes. Each item is typically assigned a call number, which identifies the location of the item within the system. Materials can be arranged by many different factors, typically in either a hierarchical tree structure based on the subject or using a faceted classification system, which allows the assignment of multiple classifications to an object, enabling the classifications to be ordered in many ways. == Description == Library classification is an important and crucial aspect in library and information science. It is distinct from scientific classification in that it has as its goal to provide a useful ordering of documents rather than a theoretical organization of knowledge. Although it has the practical purpose of creating a physical ordering of documents, it does generally attempt to adhere to accepted scientific knowledge. Library classification helps to accommodate all the newly published literature in an already created order of arrangement in a filial sequence. Library classification can be defined as the arrangement of books on shelves, or description of them, in the manner which is most useful to those who read with the ultimate aim of grouping similar things together. Library classification is meant to achieve these four purposes: ordering the fields of knowledge in a systematic way, bring related items together in the most helpful sequence, provide orderly access on the shelf, and provide a location for an item on the shelf. Library classification is distinct from the application of subject headings in that classification organizes knowledge into a systematic order, while subject headings provide access to intellectual materials through vocabulary terms that may or may not be organized as a knowledge system. The characteristics that a bibliographic classification demands for the sake of reaching these purposes are: a useful sequence of subjects at all levels, a concise memorable notation, and a host of techniques and devices of number synthesis. == History == Library classifications were preceded by classifications used by bibliographers such as Conrad Gessner. The earliest library classification schemes organized books in broad subject categories. The earliest known library classification scheme is the Pinakes by Callimachus, a scholar at the Library of Alexandria during the third century BC. During the Renaissance and Reformation era, "Libraries were organized according to the whims or knowledge of individuals in charge." This changed the format in which various materials were classified. Some collections were classified by language and others by how they were printed. After the printing revolution in the sixteenth century, the increase in available printed materials made such broad classification unworkable, and more granular classifications for library materials had to be developed in the nineteenth century. In 1627 Gabriel Naudé published a book called Advice on Establishing a Library. At the time, he was working in the private library of Président à mortier Henri de Mesmes II. Mesmes had around 8,000 printed books and many more Greek, Latin and French written manuscripts. Although it was a private library, scholars with references could access it. The purpose of Advice on Establishing a Library was to identify rules for private book collectors to organize their collections in a more orderly way to increase the collection's usefulness and beauty. Naudé developed a classification system based on seven different classes: theology, medicine, jurisprudence, history, philosophy, mathematics, and the humanities. These seven classes would later be increased to twelve. Advice on Establishing a Library was about a private library, but within the same book, Naudé encouraged the idea of public libraries open to all people regardless of their ability to pay for access to the collection. One of the most famous libraries that Naudé helped improve was the Bibliothèque Mazarine in Paris. Naudé spent ten years there as a librarian. Because of Naudé's strong belief in free access to libraries to all people, the Bibliothèque Mazarine became the first public library in France around 1644. Although libraries created order within their collections from as early as the fifth century BC, the Paris Bookseller's classification, developed in 1842 by Jacques Charles Brunet, is generally seen as the first of the modern book classifications. Brunet provided five major classes: theology, jurisprudence, sciences and arts, belles-lettres, and history. Classification can now be seen as a provider of subject access to information in a networked environment. == Types == There are many standard systems of library classification in use, and many more have been proposed over the years. However, in general, classification systems can be divided into three types depending on how they are used: === Universal schemes === Covers all subjects, e.g. the Dewey Decimal Classification (DDC), Universal Decimal Classification (UDC), and Colon Classification (CC). === Specific classification schemes === Covers particular subjects or types of materials, e.g. Iconclass (art), British Catalogue of Music Classification, and Dickinson classification (music), or the NLM Classification (medicine). === National schemes === Specially created for certain countries, e.g. Swedish library classification system, SAB (Sveriges Allmänna Biblioteksförening). The Library of Congress Classification was designed around the collection of the US Library of Congress and has an American, European, and Christian bias. Nevertheless, it is used widely in large academic and research libraries. In terms of functionality, classification systems are often described as: === Enumerative === Subject headings are listed alphabetically, with numbers assigned to each heading in alphabetical order. === Hierarchical === Subjects are divided hierarchically, from most general to most specific. === Faceted/analytico-synthetic === Subjects are divided into mutually exclusive orthogonal facets. There are few completely enumerative systems or faceted systems; most systems are a blend but favouring one type or the other. The most common classification systems, LCC and DDC, are essentially enumerative, though with some hierarchical and faceted elements (more so for DDC), especially at the broadest and most general level. The first true faceted system was the colon classification of S. R. Ranganathan. == Methods or systems == Classification types denote the classification or categorization according to the form or characteristics or qualities of a classification scheme or schemes. Method and system has similar meaning. Method or methods or system means the classification schemes like Dewey Decimal Classification or Universal Decimal Classification. The types of classification is for identifying and understanding or education or research purposes while classification method means those classification schemes like DDC, UDC. === English language universal classification systems === The most common systems in English-speaking countries are: Dewey Decimal Classification (DDC) Library of Congress Classification (LCC) Universal Decimal Classification (UDC) Other systems include: Book Industry Standards and Communications (BISAC), originally developed for use by U.S. booksellers, has become increasingly popular in libraries. Bliss bibliographic classification used in some British libraries Colon classification (CC) Garside classification used in most libraries of University College London Gladstone Library Classification, devised by W.E. Gladstone and used exclusively at Gladstone's Library Harvard-Yenching Classification, an English classification system for Chinese language materials === Non-English universal classification systems === German Regensburger Verbundklassifikation (RVK) A system of book classification for Chinese libraries (Liu's Classification) library classification for user New Classification Scheme for Chinese Libraries Nippon Decimal Classification (NDC) Chinese Library Classification (CLC) Korean Decimal Classification (KDC) Russian Library-Bibliographical Classification (BBK) Swedish library classification system (SAB) === Universal classification systems that rely on synthesis (faceted systems) === Bliss bibliographic classification Colon classification Cutter Expansive Classification Universal Decimal Classification Newer classification systems tend to use the principle of synthesis (combining codes from different lists to represent the different attributes of a work) heavily, which is comparatively lacking in LC or DDC. == Practice == Library classification is associated with library (descriptive) cataloging under the rubric of cataloging and classification, sometimes grouped together as technical serv
Catastrophic interference
Catastrophic interference, also known as catastrophic forgetting, is the tendency of an artificial neural network to abruptly and drastically forget previously learned information upon learning new information. Neural networks are an important part of the connectionist approach to cognitive science. The issue of catastrophic interference when modeling human memory with connectionist models was originally brought to the attention of the scientific community by research from McCloskey and Cohen (1989), and Ratcliff (1990). It is a radical manifestation of the 'sensitivity-stability' dilemma or the 'stability-plasticity' dilemma. Specifically, these problems refer to the challenge of making an artificial neural network that is sensitive to, but not disrupted by, new information. Lookup tables and connectionist networks lie on the opposite sides of the stability plasticity spectrum. The former remains completely stable in the presence of new information but lacks the ability to generalize, i.e. infer general principles, from new inputs. On the other hand, connectionist networks like the standard backpropagation network can generalize to unseen inputs, but they are sensitive to new information. Backpropagation models can be analogized to human memory insofar as they have a similar ability to generalize, but these networks often exhibit less stability than human memory. Notably, these backpropagation networks are susceptible to catastrophic interference. This is an issue when modelling human memory, because unlike these networks, humans typically do not show catastrophic forgetting. == Discovery == The term catastrophic interference was originally coined by McCloskey and Cohen (1989) but was also brought to the attention of the scientific community by research from Ratcliff (1990). === The Sequential Learning Problem: McCloskey and Cohen (1989) === McCloskey and Cohen (1989) noted the problem of catastrophic interference during two different experiments with backpropagation neural network modelling. Experiment 1: Learning the ones and twos addition facts In their first experiment they trained a standard backpropagation neural network on a single training set consisting of 17 single-digit ones problems (i.e., 1 + 1 through 9 + 1, and 1 + 2 through 1 + 9) until the network could represent and respond properly to all of them. The error between the actual output and the desired output steadily declined across training sessions, which reflected that the network learned to represent the target outputs better across trials. Next, they trained the network on a single training set consisting of 17 single-digit twos problems (i.e., 2 + 1 through 2 + 9, and 1 + 2 through 9 + 2) until the network could represent, respond properly to all of them. They noted that their procedure was similar to how a child would learn their addition facts. Following each learning trial on the twos facts, the network was tested for its knowledge on both the ones and twos addition facts. Like the ones facts, the twos facts were readily learned by the network. However, McCloskey and Cohen noted the network was no longer able to properly answer the ones addition problems even after one learning trial of the twos addition problems. The output pattern produced in response to the ones facts often resembled an output pattern for an incorrect number more closely than the output pattern for a correct number. This is considered to be a drastic amount of error. Furthermore, the problems 2+1 and 1+2, which were included in both training sets, even showed dramatic disruption during the first learning trials of the twos facts. Experiment 2: Replication of Barnes and Underwood (1959) study In their second connectionist model, McCloskey and Cohen attempted to replicate the study on retroactive interference in humans by Barnes and Underwood (1959). They trained the model on A-B and A-C lists and used a context pattern in the input vector (input pattern), to differentiate between the lists. Specifically the network was trained to respond with the right B response when shown the A stimulus and A-B context pattern and to respond with the correct C response when shown the A stimulus and the A-C context pattern. When the model was trained concurrently on the A-B and A-C items then the network readily learned all of the associations correctly. In sequential training the A-B list was trained first, followed by the A-C list. After each presentation of the A-C list, performance was measured for both the A-B and A-C lists. They found that the amount of training on the A-C list in Barnes and Underwood study that lead to 50% correct responses, lead to nearly 0% correct responses by the backpropagation network. Furthermore, they found that the network tended to show responses that looked like the C response pattern when the network was prompted to give the B response pattern. This indicated that the A-C list apparently had overwritten the A-B list. This could be likened to learning the word dog, followed by learning the word stool and then finding that you think of the word stool when presented with the word dog. McCloskey and Cohen tried to reduce interference through a number of manipulations including changing the number of hidden units, changing the value of the learning rate parameter, overtraining on the A-B list, freezing certain connection weights, changing target values 0 and 1 instead 0.1 and 0.9. However, none of these manipulations satisfactorily reduced the catastrophic interference exhibited by the networks. Overall, McCloskey and Cohen (1989) concluded that: at least some interference will occur whenever new learning alters the weights involved in representing old learning the greater the amount of new learning, the greater the disruption in old knowledge interference was catastrophic in the backpropagation networks when learning was sequential but not concurrent === Constraints Imposed by Learning and Forgetting Functions: Ratcliff (1990) === Ratcliff (1990) used multiple sets of backpropagation models applied to standard recognition memory procedures, in which the items were sequentially learned. After inspecting the recognition performance models he found two major problems: Well-learned information was catastrophically forgotten as new information was learned in both small and large backpropagation networks. Even one learning trial with new information resulted in a significant loss of the old information, paralleling the findings of McCloskey and Cohen (1989). Ratcliff also found that the resulting outputs were often a blend of the previous input and the new input. In larger networks, items learned in groups (e.g. AB then CD) were more resistant to forgetting than were items learned singly (e.g. A then B then C...). However, the forgetting for items learned in groups was still large. Adding new hidden units to the network did not reduce interference. Discrimination between the studied items and previously unseen items decreased as the network learned more. This finding contradicts studies on human memory, which indicated that discrimination increases with learning. Ratcliff attempted to alleviate this problem by adding 'response nodes' that would selectively respond to old and new inputs. However, this method did not work as these response nodes would become active for all inputs. A model which used a context pattern also failed to increase discrimination between new and old items. == Proposed solutions == The main cause of catastrophic interference seems to be overlap in the representations at the hidden layer of distributed neural networks. In a distributed representation, each input tends to create changes in the weights of many of the nodes. Catastrophic forgetting occurs because when many of the weights where "knowledge is stored" are changed, it is unlikely for prior knowledge to be kept intact. During sequential learning, the inputs become mixed, with the new inputs being superimposed on top of the old ones. Another way to conceptualize this is by visualizing learning as a movement through a weight space. This weight space can be likened to a spatial representation of all of the possible combinations of weights that the network could possess. When a network first learns to represent a set of patterns, it finds a point in the weight space that allows it to recognize all of those patterns. However, when the network then learns a new set of patterns, it will move to a place in the weight space for which the only concern is the recognition of the new patterns. To recognize both sets of patterns, the network must find a place in the weight space suitable for recognizing both the new and the old patterns. Below are a number of techniques which have empirical support in successfully reducing catastrophic interference in backpropagation neural networks: === Orthogonality === Many of the early techniques in reducing representational overlap involved making either the input vecto
GuideGeek
GuideGeek is an AI-powered travel assistant that was launched by travel publisher Matador Network in April 2023 and is accessed by users through Instagram, WhatsApp and Facebook Messenger to plan itineraries or provide travel tips and recommendations. It uses generative artificial intelligence technology from OpenAI. Matador Network is a San Francisco-based digital media company and online travel publication with millions of monthly visitors and social media followers. == Features == Users message GuideGeek questions about travel and receive customized answers and itineraries that are pulled from ChatGPT in addition to over 1,000 additional travel-specific integrations such as live flight, hotel and vacation rental data. Travelers can specify their budget and needs to generate custom itineraries. GuideGeek is not an app and does not require the user to download anything, instead relying on messaging apps such as Instagram to connect users with the AI. GuideGeek is free to use, doesn't include ads, and doesn't sell user data. Matador Network has a team of staff members monitoring conversations to correct them if the AI makes a false statement; for example, one user incorrectly inputted “Crete Freeze” instead of “Crete, Greece”, and the AI made up a fictional soft serve company. Using a technique known as reinforcement learning from human feedback (RLHF), the accuracy of GuideGeek increased to 98%, according to Matador Network CEO, Ross Borden. == Destination partnerships == Matador Network is monetizing GuideGeek via white-label partnerships with tourism bureaus and destination marketing organizations (DMOs). As of March 2024, it had over a dozen such clients. Estes Park, Colorado, was one of the first DMOs to partner with Matador for a custom version of GuideGeek called “Rocky Mountain Roamer.” For Discover Greece, Matador created Pythia, a custom AI named after the high priestess of the Temple of Apollo at Delphi. As Borden explained to Travel + Leisure, “Visitors to the Discover Greece website will find Pythia in the bottom right corner, and they can converse with the AI like a friend who knows everything about Greece.” Other DMOs who have partnerships with GuideGeek include the Aruba Tourism Authority, Visit Reno Tahoe, Illinois Office of Tourism, and Tourism Richmond. == Awards == In recognition of GuideGeek, Fast Company named Matador Network to its 2024 list of Most Innovative Companies. Following growth driven by the launch of GuideGeek, Matador Network was ranked on the 2024 Inc. 5000 list of fastest-growing private companies in America. The 2024 Skift IDEA Awards recognized Matador Network as a finalist in the category of Best Use of AI for GuideGeek's customized AI for the travel industry. == Michael Motamedi experiment == Travel influencer and chef Michael Motamedi traveled the world with his wife Vanessa Salas and their 2-year-old daughter on a six-month trip (which was later extended to a full year) led by GuideGeek. The family started off in Morocco before heading to Spain and continuing east. The experiment became the basis of a web series called “No Fixed Address.” Motamedi used GuideGeek's AI to select countries the family visited, where they ate, and what sites they saw. Motamedi and Salas first tested out the technology in April 2023 while using the chatbot to plan a date night in Mexico City. GuideGeek provided speakeasy and drink recommendations as well as local history facts.
Text simplification
Text simplification is an aspect of natural language processing that involves modifying, organizing, or categorizing existing text to make it easier to understand while retaining its original meaning. This process is essential in today's world, where communication is increasingly complex due to advancements in science, technology, and media. Human languages are inherently intricate, with extensive vocabularies and complex structures that can be challenging for machines to handle efficiently. Researchers have found that semantic compression techniques can help streamline and simplify text by reducing linguistic diversity and simplifying the vocabulary used in a given context. == Example == Text simplification involves modifying complex sentences into simpler ones to enhance readability and comprehension. Siddharthan (2006) provides an example to illustrate this process. The original sentence contains multiple clauses and phrases, which can be broken down into simpler sentences for better understanding. Also contributing to the firmness in copper, the analyst noted, was a report by Chicago purchasing agents, which precedes the full purchasing agents report that is due out today and gives an indication of what the full report might hold. Also contributing to the firmness in copper, the analyst noted, was a report by Chicago purchasing agents. The Chicago report precedes the full purchasing agents report. The Chicago report gives an indication of what the full report might hold. The full report is due out today. An approach to text simplification involves lexical simplification via lexical substitution, a process that replaces complex words with simpler synonyms. Identifying complex words is a challenge addressed by machine learning classifiers trained on labeled data. Researchers have found that asking labelers to sort words by complexity levels yields more consistent results than the traditional method of categorizing words as simple or complex.
Liang Wenfeng
Liang Wenfeng (Chinese: 梁文锋; pinyin: Liáng Wénfēng; born 1985) is a Chinese entrepreneur and businessman who is the co-founder of the quantitative hedge fund High-Flyer, as well as the founder and CEO of its artificial intelligence company DeepSeek. Liang attended Zhejiang University, and began his career by applying machine learning methods to quantitative finance. Through High-Flyer, he built large-scale computing infrastructure that was later used to support artificial intelligence research, leading to the creation of DeepSeek in 2023. DeepSeek gained international attention following the release of DeepSeek-R1, which analysts described as demonstrating high-level performance with comparatively limited compute resources. In 2025, Liang was named to Time magazine's list of 100 Most Influential People in AI and Fortune's list of the Most Powerful People in Business. == Early life == Liang was born in 1985 in the village of Mililing (米历岭村), Qinba town (覃巴镇), Wuchuan city (吴川市), Guangdong. His parents were both primary school teachers. Liang was routinely praised by both locals and teachers alike. Even since middle school, Liang was recalled for being well-known for reading comic books, while also being very proficient in mathematics. == Education == After elementary school, Liang attended Wuchuan No. 1 Middle School. There, he quickly excelled in class and ranked highly amongst his peers. He taught himself high school and university-level mathematics courses. Liang then attended Wuchaun No. 1 High School. In these years, he developed hobbies of mathematical modeling and conducting research projects. Compared to his peers, he was always ranked highly. For every mathematics exam, he always ranked within the top three. He was also the top scorer in the Zhanjiang region of Guangdong for the college entrance exam. Thus, in 2002, Liang left high school early to further pursue his education at the university level at the young age of 17. Attending Zhejiang University at the age of 17, Liang earned a Bachelor of Engineering in Electronic Information Engineering in 2007 and his Master of Engineering in Information & Communication Engineering in 2010. His master's dissertation was titled "Study on Object Tracking Algorithm Based on Low-Cost PTZ camera" (基于低成本PTZ摄像机的目标跟踪算法研究). In his college years, DJI founder Wang Tao asked Liang to join as a co-founder. Liang declined the invitation to pursue artificial intelligence methodologies in financial markets. While he states that those around him had entrepreneurial mindsets, he himself valued academics. == Career == === Early career (2008–2016) === During the 2008 financial crisis, Liang formed a team with his classmates to accumulate data related to financial markets. He also led the team to explore quantitative trading using machine learning and other technologies. After his graduation, Liang moved to a cheap flat in Chengdu, Sichuan, where he experimented with ways to apply AI to various fields. These ventures failed, until he tried applying AI to finance. In 2013, Liang attempted to integrate artificial intelligence with quantitative trading and founded Hangzhou Yakebi Investment Management Co Ltd with Xu Jin, an alumnus of Zhejiang University. In 2015, they co-founded Hangzhou Huanfang Technology Co Ltd, which is today's Zhejiang Jiuzhang Asset Management Co Ltd. === High-Flyer (2016–2023) === In February 2016, Liang and two other engineering classmates co-founded Ningbo High-Flyer Quantitative Investment Management Partnership (Limited Partnership). The team relied on mathematics and AI to make investments. Much of the early startup culture was described by former employees to be "geeky" and "quirky," often seen as contrary to the existing culture in large Chinese tech companies. In 2019, Liang founded High-Flyer AI which was dedicated to research on AI algorithms and its basic applications. By this time, High-Flyer had over 10 billion yuan in assets under management. On 30 August 2019, Liang Wenfeng delivered a keynote speech entitled "The Future of Quantitative Investment in China from a Programmer's Perspective" at the Private Equity Golden Bull Award ceremony held by China Securities Journal, and sparked heated discussions. Liang stated that the criterion for determining what is quantitative or non-quantitative is whether the investment decision is made by quantitative methods or by people. Quantitative funds do not have portfolio managers making the decisions and instead are just servers. He also stated High-Flyer's mission is to improve the effectiveness of China's secondary market. In February 2021, Gregory Zuckerman's book The Man Who Solved the Market: How Jim Simons Launched the Quant Revolution was published. Liang wrote the preface for the Chinese edition of the book where he stated that whenever he encountered difficulties at work, he would think of Simons' words "There must be a way to model prices". In January 2025, Zuckerman wrote in The Wall Street Journal where he acknowledged this fact and stated he has been trying to get in touch with Liang but much like Simons, Liang is very secretive and difficult to contact. During 2021, Liang started buying thousands of Nvidia GPUs for his AI side project while running High-Flyer. Liang wanted to build something and it will be a game changer which his business partners thought was only possible from giants such as ByteDance and Alibaba Group. === DeepSeek (since 2023) === ==== DeepSeek begins ==== In May 2023, Liang announced High-Flyer would pursue the development of artificial general intelligence and launched DeepSeek. During that month in an interview with 36Kr, Liang stated that High-Flyer had acquired 10,000 Nvidia A100 GPUs before the US government imposed AI chip restrictions on China. That laid the foundation for DeepSeek to operate as an LLM developer. Liang also stated DeepSeek gets funding from High-Flyer. This was because when DeepSeek was founded, venture capital firms were reluctant in providing funding as it was unlikely that it would be able to generate an exit in a short period of time. Liang only personally holds 1% of the company, with 99% of the company being held by Ningbo High-Flyer Quantitative Investment Management Partnership (Limited Partnership). With DeepSeek's funding model, it lacks commercial pressure and rigid key performance indicators, enabling the company to deviate from previously established model architectures. ==== Early development ==== In July 2024, Liang was interviewed again by 36Kr. He stated that when DeepSeek-V2 was released and triggered an AI price war in China, it came as a huge surprise as the team did not expect pricing to be so sensitive. Liang's aggressive pricing of the language model forced domestic tech giants including Alibaba and Baidu to cut their own rates by over 95%. He also stated that as China's economy develops, it should gradually become a contributor instead of freeriding. What is lacking in China's innovation is not capital but a lack of confidence and knowledge on organizing talent into it. DeepSeek has not hired anyone particularly special and employees tend to be locally educated. When it comes to disruptive technologies, closed source approaches can only temporarily delay others in catching up. As the goal was long-term, DeepSeek sought employees who had ability and passion rather than experience. To retain a high talent density relative to larger firms like Bytedance or Baidu, DeepSeek aimed to maintain a low-hierarchy corporate culture, with members working in project-based groups, as well as competitive compensation. Liang emphasized his vision for DeepSeek employees to bring their "unique experience and ideas" instead of needing to be explicitly directed, with an overall bottom-up approach to division of labor. Liang noted that a significant outcome of this approach was the multi-head latent attention training architecture, which was attributed directly to a young DeepSeek researcher's personal interest. This advancement played a core role in reducing the cost of training the DeepSeek-V3 model, released in December 2024. ==== Release of DeepSeek-R1 ==== Also on 20 January 2025, DeepSeek, the company Liang founded and served as the CEO, released DeepSeek-R1, a 671-billion-parameter open-source reasoning AI model, alongside the publication of a detailed technical paper explaining its architecture and training methodology. The model was built using just 2,048 Nvidia H800 GPUs at a cost of $5.6 million, showcasing a resource-efficient approach that contrasted sharply with the billion-dollar budgets of Western competitors. The development of DeepSeek-R1 occurred amidst U.S. sanctions where Trump limited sales of Nvidia chips to China. By 27 January, DeepSeek surpassed ChatGPT to become the #1 free app on the United States iOS App Store. U.S. stocks plummeted, as more than $1 trillion was erased in market capitalization amid panic over DeepSeek. Technology journ