Teleradiology is the transmission of radiological patient images from procedures such as x-rays, Computed tomography (CT), and MRI imaging, from one location to another for the purposes of sharing studies with other radiologists and physicians. Teleradiology allows radiologists to provide services without actually having to be at the location of the patient. This is particularly important when a sub-specialist such as an MRI radiologist, neuroradiologist, pediatric radiologist, or musculoskeletal radiologist is needed, since these professionals are generally only located in large metropolitan areas working during daytime hours. Teleradiology allows for specialists to be available at all times. Teleradiology utilizes standard network technologies such as the Internet, telephone lines, wide area networks, local area networks (LAN) and the latest advanced technologies such as medical cloud computing. Specialized software is used to transmit the images and enable the radiologist to effectively analyze potentially hundreds of images of a given study. Technologies such as advanced graphics processing, voice recognition, artificial intelligence, and image compression are often used in teleradiology. Through teleradiology and mobile DICOM viewers, images can be sent to another part of the hospital or to other locations around the world with equal effort. Teleradiology is a growth technology given that imaging procedures are growing approximately 15% annually against an increase of only 2% in the radiologist population. == Reports == Teleradiology services commonly provide either preliminary or final interpretations of medical imaging studies. Preliminary reads are frequently used in emergency settings to support immediate clinical decisions and may include direct communication of critical findings to the referring physician. Some providers report turnaround times of approximately 30 minutes for emergency cases, with faster processing for time-sensitive conditions such as stroke. Final reads are definitive and used in official patient records and billing. These reports typically include all relevant findings and may require access to prior imaging and clinical data. Teleradiology is also employed to provide off-hour or overflow coverage for healthcare institutions lacking continuous on-site radiology staffing. == Subspecialties == Some teleradiologists are fellowship trained and have a wide variety of subspecialty expertise including such difficult-to-find areas as neuroradiology, pediatric neuroradiology, thoracic imaging, musculoskeletal radiology, mammography, and nuclear cardiology. There are also various medical practitioners who are not radiologists that take on studies in radiology to become sub specialists in their respected fields, an example of this is dentistry where oral and maxillofacial radiology allows those in dentistry to specialize in the acquisition and interpretation of radiographic imaging studies performed for diagnosis of treatment guidance for conditions affecting the maxillofacial region. == Teleultrasound == Teleradiology infrastructure has also been adapted to support point-of-care ultrasound (POCUS) in remote and austere environments. In teleultrasound—also known as telementored ultrasound—a remote expert guides a non-specialist in real time during image acquisition. This technique has been successfully demonstrated in extreme settings, including aboard the International Space Station, on Mount Everest, and during helicopter flight. == Regulations == In the United States, Medicare and Medicaid laws require the teleradiologist to be on U.S. soil in order to qualify for reimbursement of the Final Read. In addition, advanced teleradiology systems must also be HIPAA compliant, which helps to ensure patients' privacy. HIPAA (Health Insurance Portability and Accountability Act of 1996) is a uniform, federal floor of privacy protections for consumers. It limits the ways that entities can use patients' personal information and protects the privacy of all medical information no matter what form it is in. Quality teleradiology must abide by important HIPAA rules to ensure patients' privacy is protected. Also State laws governing the licensing requirements and medical malpractice insurance coverage required for physicians vary from state to state. Ensuring compliance with these laws is a significant overhead expense for larger multi-state teleradiology groups. Medicare (Australia) has identical requirements to that of the United States, where the guidelines are provided by the Department of Health and Ageing, and government based payments fall under the Health Insurance Act. The regulations in Australia are also conducted at both federal and state levels, ensuring that strict guidelines are adhered to at all times, with regular yearly updates and amendments are introduced (usually around March and November of every year), ensuring that the legislation is kept up to date with changes in the industry. One of the most recent changes to Medicare and radiology / teleradiology in Australia was the introduction of the Diagnostic Imaging Accreditation Scheme (DIAS) on 1 July 2008. DIAS was introduced to further improve the quality of Diagnostic Imaging and to amend the Health Insurance Act. == Industry growth == Until the late 1990s teleradiology was primarily used by individual radiologists to interpret occasional emergency studies from offsite locations, often in the radiologists home. The connections were made through standard analog phone lines. Teleradiology expanded rapidly as the growth of the internet and broad band combined with new CT scanner technology to become an essential tool in trauma cases in emergency rooms throughout the country. The occasional 2–3 x-ray studies a week soon became 3–10 CT scans, or more, a night. Because ER physicians are not trained to read CT scans or MRIs, radiologists went from working 8–10 hours a day, five and half days a week to a schedule of 24 hours a day, 7 days a week coverage. This became a particularly acute challenge in smaller rural facilities that only had one solo radiologist with no other to share call. These circumstances spawned a post-dot.com boom of firms and groups that provided medical outsourcing, off-site teleradiology on-call services to hospitals and Radiology Groups around the country. As an example, a teleradiology firm might cover trauma at a hospital in Indiana with doctors based in Texas. Some firms even used overseas doctors in locations like Australia and India. Nighthawk, founded by Paul Berger, was the first to station U.S. licensed radiologists overseas (initially Australia and later Switzerland) to maximize the time zone difference to provide nightcall in U.S. hospitals. Currently, teleradiology firms are facing pricing pressures. Industry consolidation is likely as there are more than 500 of these firms, large and small, throughout the United States.
I Am Rich
I Am Rich is a discontinued 2008 mobile app for iPhones which had minimal function and was priced at US$999.99 (equivalent to $1,495 in 2025). The app was pulled from the App Store less than 24 hours after its launch. Receiving negative reviews from critics, only eight copies were sold. In the years since, several similar applications have been released at lower prices. == Overview == I Am Rich was developed as a joke by German software developer, Armin Heinrich, after he saw iPhone users complaining about software priced above $0.99. The app only showed a glowing red gem and an icon that, when pressed, displayed the following mantra in large text: I am richI deserv [sic] itI am good,healthy & successful Heinrich told The New York Times that "I regard it as art. I did not expect many people to buy it and did not expect all the fuss about it." The application is described as "a work of art with no hidden function at all", with its only purpose being to show other people that they were able to afford it. Vox writer Zachary Crockett called it "the ultimate Veblen good in app form". == Release == Heinrich released and distributed I Am Rich through the App Store on 5 August 2008. The app was sold for US$999.99 (equivalent to $1,495 in 2025), €799.99 (equivalent to €1,078 in 2023), and £599.99 (equivalent to £978.12 in 2025)—the highest prices Apple allowed for App Store content. Without explanation, the application was removed from the App Store by Apple less than a day after its release. === Purchases === Eight people bought the application, at least one of whom claimed to have done so accidentally. Six US sales and two European sales netted $5,600 for Heinrich and $2,400 for Apple (respectively equivalent to $8,374 and $3,589 in 2025). In correspondence with the Los Angeles Times, Heinrich told the newspaper that Apple had refunded two purchasers of his app, and that he was happy to not have dissatisfied customers. == Reception == Discussing the app on the website Silicon Alley Insider, Dan Frommer described the program as a "scam", "worthless", and finally "a joke that smells like a scammy rip-off" on August 5, 6, and 8, respectively. Without purchasing the app, Fox News's Paul Wagenseil guessed that the secret mantra was "German for 'Sucker!'" (Heinrich is German). Wired's Brian X. Chen described I Am Rich as a waste of money to "prove you're a jerk", and contrasted the expenditure with donating to cancer foundations and Third World countries. Heinrich told the Los Angeles Times's Mark Milian that he had received correspondence from satisfied customers: "I've got e-mails from customers telling me that they really love the app [... and that they had] no trouble spending the money". In an interview with The New York Times, though, he told of receiving many insulting emails and telephone messages. == Similar applications == The next year, Heinrich released I Am Rich LE. Priced at US$9.99 (equivalent to $14.99 in 2025), the new app has several new features (including a calculator, "help system", and the "famous mantra without the spelling mistakes") to meet Apple's requirement that apps have "definable content". Some customers were disappointed by the new functionality, poorly rating the app due to its ostensible improvements. On 23 February 2009, CNET Asia reported on the "conceptually similar" app, I Am Richer, developed by Mike DG for Google's Android. The app was released on the Android Market for US$200 (equivalent to $300.14 in 2025), a limit imposed by Google, who had no objection to the application. With the same name, the I Am Rich that was released on the Windows Phone Marketplace on 22 December 2010, was developed by DotNetNuzzi. Described by MobileCrunch as equally useless as the original, this app cost US$499.99 (equivalent to $738.2 in 2025), the price cap imposed by Microsoft.
Semantic network
A semantic network, or frame network is a knowledge base that represents semantic relations between concepts in a network. This is often used as a form of knowledge representation. It is a directed or undirected graph consisting of vertices, which represent concepts, and edges, which represent semantic relations between concepts, mapping or connecting semantic fields. A semantic network may be instantiated as, for example, a graph database or a concept map. Typical standardized semantic networks are expressed as semantic triples. Semantic networks are used in natural language processing applications such as semantic parsing and word-sense disambiguation. Semantic networks can also be used as a method to analyze large texts and identify the main themes and topics (e.g., of social media posts), to reveal biases (e.g., in news coverage), or even to map an entire research field. == History == Examples of the use of semantic networks in logic, directed acyclic graphs as a mnemonic tool, dates back centuries. The earliest documented use being the Greek philosopher Porphyry's commentary on Aristotle's categories in the third century AD. In computing history, "Semantic Nets" for the propositional calculus were first implemented for computers by Richard H. Richens of the Cambridge Language Research Unit in 1956 as an "interlingua" for machine translation of natural languages. Although the importance of this work and the CLRU was only belatedly realized. Semantic networks were also independently implemented by Robert F. Simmons and Sheldon Klein, using the first order predicate calculus as a base, after being inspired by a demonstration of Victor Yngve. The "line of research was originated by the first President of the Association [Association for Computational Linguistics], Victor Yngve, who in 1960 had published descriptions of algorithms for using a phrase structure grammar to generate syntactically well-formed nonsense sentences. Sheldon Klein and I about 1962-1964 were fascinated by the technique and generalized it to a method for controlling the sense of what was generated by respecting the semantic dependencies of words as they occurred in text." Other researchers, most notably M. Ross Quillian and others at System Development Corporation helped contribute to their work in the early 1960s as part of the SYNTHEX project. It's from these publications at SDC that most modern derivatives of the term "semantic network" cite as their background. Later prominent works were done by Allan M. Collins and Quillian (e.g., Collins and Quillian; Collins and Loftus Quillian). Still later in 2006, Hermann Helbig fully described MultiNet. In the late 1980s, two Netherlands universities, Groningen and Twente, jointly began a project called Knowledge Graphs, which are semantic networks but with the added constraint that edges are restricted to be from a limited set of possible relations, to facilitate algebras on the graph. In the subsequent decades, the distinction between semantic networks and knowledge graphs was blurred. In 2012, Google gave their knowledge graph the name Knowledge Graph. The Semantic Link Network was systematically studied as a social semantics networking method. Its basic model consists of semantic nodes, semantic links between nodes, and a semantic space that defines the semantics of nodes and links and reasoning rules on semantic links. The systematic theory and model was published in 2004. This research direction can trace to the definition of inheritance rules for efficient model retrieval in 1998 and the Active Document Framework ADF. Since 2003, research has developed toward social semantic networking. This work is a systematic innovation at the age of the World Wide Web and global social networking rather than an application or simple extension of the Semantic Net (Network). Its purpose and scope are different from that of the Semantic Net (or network). The rules for reasoning and evolution and automatic discovery of implicit links play an important role in the Semantic Link Network. Recently it has been developed to support Cyber-Physical-Social Intelligence. It was used for creating a general summarization method. The self-organised Semantic Link Network was integrated with a multi-dimensional category space to form a semantic space to support advanced applications with multi-dimensional abstractions and self-organised semantic links It has been verified that Semantic Link Network play an important role in understanding and representation through text summarisation applications. Semantic Link Network has been extended from cyberspace to cyber-physical-social space. Competition relation and symbiosis relation as well as their roles in evolving society were studied in the emerging topic: Cyber-Physical-Social Intelligence More specialized forms of semantic networks has been created for specific use. For example, in 2008, Fawsy Bendeck's PhD thesis formalized the Semantic Similarity Network (SSN) that contains specialized relationships and propagation algorithms to simplify the semantic similarity representation and calculations. == Basics of semantic networks == A semantic network is used when one has knowledge that is best understood as a set of concepts that are related to one another. Most semantic networks are cognitively based. They also consist of arcs and nodes which can be organized into a taxonomic hierarchy. Semantic networks contributed ideas of spreading activation, inheritance, and nodes as proto-objects. == Examples == === In Lisp === The following code shows an example of a semantic network in the Lisp programming language using an association list. To extract all the information about the "canary" type, one would use the assoc function with a key of "canary". === WordNet === An example of a semantic network is WordNet, a lexical database of English. It groups English words into sets of synonyms called synsets, provides short, general definitions, and records the various semantic relations between these synonym sets. Some of the most common semantic relations defined are meronymy (A is a meronym of B if A is part of B), holonymy (B is a holonym of A if B contains A), hyponymy (or troponymy) (A is subordinate of B; A is kind of B), hypernymy (A is superordinate of B), synonymy (A denotes the same as B) and antonymy (A denotes the opposite of B). WordNet properties have been studied from a network theory perspective and compared to other semantic networks created from Roget's Thesaurus and word association tasks. From this perspective the three of them are a small world structure. === Other examples === It is also possible to represent logical descriptions using semantic networks such as the existential graphs of Charles Sanders Peirce or the related conceptual graphs of John F. Sowa. These have expressive power equal to or exceeding standard first-order predicate logic. Unlike WordNet or other lexical or browsing networks, semantic networks using these representations can be used for reliable automated logical deduction. Some automated reasoners exploit the graph-theoretic features of the networks during processing. Other examples of semantic networks are Gellish models. Gellish English with its Gellish English dictionary, is a formal language that is defined as a network of relations between concepts and names of concepts. Gellish English is a formal subset of natural English, just as Gellish Dutch is a formal subset of Dutch, whereas multiple languages share the same concepts. Other Gellish networks consist of knowledge models and information models that are expressed in the Gellish language. A Gellish network is a network of (binary) relations between things. Each relation in the network is an expression of a fact that is classified by a relation type. Each relation type itself is a concept that is defined in the Gellish language dictionary. Each related thing is either a concept or an individual thing that is classified by a concept. The definitions of concepts are created in the form of definition models (definition networks) that together form a Gellish Dictionary. A Gellish network can be documented in a Gellish database and is computer interpretable. SciCrunch is a collaboratively edited knowledge base for scientific resources. It provides unambiguous identifiers (Research Resource IDentifiers or RRIDs) for software, lab tools etc. and it also provides options to create links between RRIDs and from communities. Another example of semantic networks, based on category theory, is ologs. Here each type is an object, representing a set of things, and each arrow is a morphism, representing a function. Commutative diagrams also are prescribed to constrain the semantics. In the social sciences people sometimes use the term semantic network to refer to co-occurrence networks. == Software tools == There are also elaborate types of semantic networks connected with corresponding sets of software tools used for
United States export controls on AI chips and semiconductors
United States export controls on AI chips and semiconductors are a series of regulations imposed by the United States restricting the export of technology and equipment related to artificial intelligence to other countries, primarily targeting China. This has happened in the context of a broader trade war. In January 2026, BIS formalized a flexible license review policy for these transactions.
STUDENT
STUDENT is an early artificial intelligence program that solves algebra word problems. It is written in Lisp by Daniel G. Bobrow as his PhD thesis in 1964 (Bobrow 1964). It was designed to read and solve the kind of word problems found in high school algebra books. The program is often cited as an early accomplishment of AI in natural language processing. == Technical description == Within Project MAC at MIT, the STUDENT system was an early example of a question answering software, which uniquely involved natural language processing and symbolic programming. Other early attempts for solving algebra story problems were realized with 1960s hardware and software as well: for example, the Philips, Baseball and Synthex systems. STUDENT accepts an algebra story written in the English language as input, and generates a number as output. This is realized with a layered pipeline that consists of heuristics for pattern transformation. At first, sentences in English are converted into kernel sentences, which each contain a single piece of information. Next, the kernel sentences are converted into mathematical expressions. The knowledge base that supports the transformation contains 52 facts. STUDENT uses a rule-based system with logic inference. The rules are pre-programmed by the software developer and are able to parse natural language. More powerful techniques for natural language processing, such as machine learning, came into use later as hardware grew more capable, and gained popularity over simpler rule-based systems.
Butler in a Box
Butler in a Box was an early voice-controlled home automation device developed in 1983 by magician Gus Searcy and programmer Franz Kavan. The device allowed users to control various home electronics, such as lights and phones, using voice commands. It predated modern smart speakers and virtual assistants by several decades. == History == The idea for the Butler in a Box originated in 1983 when Searcy was asked by friends why he couldn't simply command lights to turn on and off if he could pull rabbits out of hats, given his background as a professional magician. Searcy partnered with former IBM programmer Kavan to develop the device, with their first prototype being named "Sidney". The Butler in a Box combined remote control technology with voice recognition to enable control of home devices. However, it faced challenges due to the technological limitations of the era and its high price point of nearly $1,500 (equivalent to around $3,700 in 2021). == Features and functionality == Users could activate the Butler in a Box by speaking a wake word, typically a traditional butler name, and the device would address the user as "boss". It was capable of performing tasks such as: Turning lights on and off, controlling individual zones if lights were connected to remote control modules Making and receiving phone calls Setting timers Pairing with sensors to function as a security alarm system However, the device required extensive voice training for each user, a time-consuming process compared to modern voice recognition. Additionally, settings and trained commands would be lost if power was out for over 3 hours due to the volatile memory technology used at the time. == Reception and legacy == While innovative for its time, the Butler in a Box did not achieve widespread commercial success due to its high price and the technical limitations of the 1980s. Nevertheless, it served as an important early step in the development of home automation and showcased the potential for voice-controlled technology to enhance accessibility and convenience in the home. Decades later, products like Amazon Alexa, Google Home, and Apple's Siri would make voice-controlled smart home devices commonplace and affordable, building on the groundwork laid by early attempts like the Butler in a Box.
AlphaZero
AlphaZero is a computer program developed by artificial intelligence research company DeepMind to master the games of chess, shogi and go. This algorithm uses an approach similar to AlphaGo Zero. On December 5, 2017, the DeepMind team released a preprint paper introducing AlphaZero, which would soon play three games by defeating world-champion chess engines Stockfish, Elmo, and the three-day version of AlphaGo Zero. In each case it made use of custom tensor processing units (TPUs) that the Google programs were optimized to use. AlphaZero was trained solely via self-play using 5,000 first-generation TPUs to generate the games and 64 second-generation TPUs to train the neural networks, all in parallel, with no access to opening books or endgame tables. After four hours of training, DeepMind estimated AlphaZero was playing chess at a higher Elo rating than Stockfish 8; after nine hours of training, the algorithm defeated Stockfish 8 in a time-controlled 100-game tournament (28 wins, 0 losses, and 72 draws). The trained algorithm played on a single machine with four TPUs. DeepMind's paper on AlphaZero was published in the journal Science on 7 December 2018. While the actual AlphaZero program has not been released to the public, the algorithm described in the paper has been implemented in publicly available software. In 2019, DeepMind published a new paper detailing MuZero, a new algorithm able to generalize AlphaZero's work, playing both Atari and board games without knowledge of the rules or representations of the game. == Relation to AlphaGo Zero == AlphaZero (AZ) is a more generalized variant of the AlphaGo Zero (AGZ) algorithm, and is able to play shogi and chess as well as Go. Differences between AZ and AGZ include: AZ has hard-coded rules for setting search hyperparameters. The neural network is now updated continually. AZ doesn't use symmetries, unlike AGZ. Chess or Shogi can end in a draw unlike Go; therefore, AlphaZero takes into account the possibility of a drawn game. == Stockfish and Elmo == Comparing Monte Carlo tree search searches, AlphaZero searches just 80,000 positions per second in chess and 40,000 in shogi, compared to 70 million for Stockfish and 35 million for Elmo. AlphaZero compensates for the lower number of evaluations by using its deep neural network to focus much more selectively on the most promising variation. == Training == AlphaZero was trained by simply playing against itself multiple times, using 5,000 first-generation TPUs to generate the games and 64 second-generation TPUs to train the neural networks. In parallel, the in-training AlphaZero was periodically matched against its benchmark (Stockfish, Elmo, or AlphaGo Zero) in brief one-second-per-move games to determine how well the training was progressing. DeepMind judged that AlphaZero's performance exceeded the benchmark after around four hours of training for Stockfish, two hours for Elmo, and eight hours for AlphaGo Zero. == Preliminary results == === Outcome === ==== Chess ==== In AlphaZero's chess match against Stockfish 8 (2016 TCEC world champion), each program was given one minute per move. AlphaZero was flying the English flag, while Stockfish the Norwegian. Stockfish was allocated 64 threads and a hash size of 1 GB, a setting that Stockfish's Tord Romstad later criticized as suboptimal. AlphaZero was trained on chess for a total of nine hours before the match. During the match, AlphaZero ran on a single machine with four application-specific TPUs. In 100 games from the normal starting position, AlphaZero won 25 games as White, won 3 as Black, and drew the remaining 72. In a series of twelve, 100-game matches (of unspecified time or resource constraints) against Stockfish starting from the 12 most popular human openings, AlphaZero won 290, drew 886 and lost 24. ==== Shogi ==== AlphaZero was trained on shogi for a total of two hours before the tournament. In 100 shogi games against Elmo (World Computer Shogi Championship 27 summer 2017 tournament version with YaneuraOu 4.73 search), AlphaZero won 90 times, lost 8 times and drew twice. As in the chess games, each program got one minute per move, and Elmo was given 64 threads and a hash size of 1 GB. ==== Go ==== After 34 hours of self-learning of Go and against AlphaGo Zero, AlphaZero won 60 games and lost 40. === Analysis === DeepMind stated in its preprint, "The game of chess represented the pinnacle of AI research over several decades. State-of-the-art programs are based on powerful engines that search many millions of positions, leveraging handcrafted domain expertise and sophisticated domain adaptations. AlphaZero is a generic reinforcement learning algorithm – originally devised for the game of go – that achieved superior results within a few hours, searching a thousand times fewer positions, given no domain knowledge except the rules." DeepMind's Demis Hassabis, a chess player himself, called AlphaZero's play style "alien": It sometimes wins by offering counterintuitive sacrifices, like offering up a queen and bishop to exploit a positional advantage. "It's like chess from another dimension." Given the difficulty in chess of forcing a win against a strong opponent, the +28 –0 =72 result is a significant margin of victory. However, some grandmasters, such as Hikaru Nakamura and Komodo developer Larry Kaufman, downplayed AlphaZero's victory, arguing that the match would have been closer if the programs had access to an opening database (since Stockfish was optimized for that scenario). Romstad additionally pointed out that Stockfish is not optimized for rigidly fixed-time moves and the version used was a year old. Similarly, some shogi observers argued that the Elmo hash size was too low, that the resignation settings and the "EnteringKingRule" settings (cf. shogi § Entering King) may have been inappropriate, and that Elmo is already obsolete compared with newer programs. === Reaction and criticism === Papers headlined that the chess training took only four hours: "It was managed in little more than the time between breakfast and lunch." Wired described AlphaZero as "the first multi-skilled AI board-game champ". AI expert Joanna Bryson noted that Google's "knack for good publicity" was putting it in a strong position against challengers. "It's not only about hiring the best programmers. It's also very political, as it helps make Google as strong as possible when negotiating with governments and regulators looking at the AI sector." Human chess grandmasters generally expressed excitement about AlphaZero. Danish grandmaster Peter Heine Nielsen likened AlphaZero's play to that of a superior alien species. Norwegian grandmaster Jon Ludvig Hammer characterized AlphaZero's play as "insane attacking chess" with profound positional understanding. Former champion Garry Kasparov said, "It's a remarkable achievement, even if we should have expected it after AlphaGo." Grandmaster Hikaru Nakamura was less impressed, stating: "I don't necessarily put a lot of credibility in the results simply because my understanding is that AlphaZero is basically using the Google supercomputer and Stockfish doesn't run on that hardware; Stockfish was basically running on what would be my laptop. If you wanna have a match that's comparable you have to have Stockfish running on a supercomputer as well." Top US correspondence chess player Wolff Morrow was also unimpressed, claiming that AlphaZero would probably not make the semifinals of a fair competition such as TCEC where all engines play on equal hardware. Morrow further stated that although he might not be able to beat AlphaZero if AlphaZero played drawish openings such as the Petroff Defence, AlphaZero would not be able to beat him in a correspondence chess game either. Motohiro Isozaki, the author of YaneuraOu, noted that although AlphaZero did comprehensively beat Elmo, the rating of AlphaZero in shogi stopped growing at a point which is at most 100–200 higher than Elmo. This gap is not that high, and Elmo and other shogi software should be able to catch up in 1–2 years. == Final results == DeepMind addressed many of the criticisms in their final version of the paper, published in December 2018 in Science. They further clarified that AlphaZero was not running on a supercomputer; it was trained using 5,000 tensor processing units (TPUs), but only ran on four TPUs and a 44-core CPU in its matches. === Chess === In the final results, Stockfish 9 dev ran under the same conditions as in the TCEC superfinal: 44 CPU cores, Syzygy endgame tablebases, and a 32 GB hash size. Instead of a fixed time control of one move per minute, both engines were given 3 hours plus 15 seconds per move to finish the game. AlphaZero ran on a much more powerful machine with four TPUs in addition to 44 CPU cores. In a 1000-game match, AlphaZero won with a score of 155 wins, 6 losses, and 839 draws. DeepMind also played a series of games using the TCEC opening positions; AlphaZero also won