In machine learning and deep learning, compute is the amount of computing power or computational resources required to train machine learning models and large language models. More broadly, compute is the computational power or resources necessary for a computer or computer program to function. == Definition == Compute is commonly defined as the amount of computing power or computational resources required to train machine learning and large language models. The term "compute" has also been more broadly applied to cloud computing, referencing processing power, memory, networking, storage, and other resources required for the computation of any program. Compute is measured in petaflop/s-days and is used to document AI training. A petaflop/s-day (pfs-day) consists of performing 1015 neural net operations per second for one day, or a total of about 1020 operations. The compute-time product serves as a mental convenience, similar to kilowatt-hour for energy. An amount of compute is meant to give an idea of the number of actual operations performed. == History == In a 2018 analysis titled "AI and compute", artificial intelligence company OpenAI introduced the concept of compute. OpenAI identified two eras of training AI systems in terms of compute-usage. From 1959 to 2012, compute roughly followed Moore’s law. Between 2012 and 2018, the amount of compute used in the largest AI training runs increased exponentially, growing by more than 300,000 times — roughly doubling every 3.4 months. By comparison, Moore’s Law doubled every two years over the same period. One of the largest models, released in 2020, used 600,000 times more computing power than the 2012 model. After 2020, compute growth began to slow down, with the compute needed for the largest AI models continuing to slow down in 2023. The notion of compute has become increasingly used from the mid-2020s onwards. == Compute growth and AI progress == Larger AI models trained on more data and using more computational resources, tend to perform better. This happens even if the algorithms themselves remain unchanged. As early as 2018, OpenAI noted the exponential increase in compute to be have a key role in AI progress. OpenAI considers three factors drive the advance of AI: algorithmic innovation, data, and the amount of compute available for training. AI models with more compute not only improve in the tasks they were trained on but can develop emergent abilities. Incremental improvements can lead to more abrupt leaps in capabilities. AI provider SpaceXAI said in 2026 that their AI progress is driven by compute and used it a key metric in the AI training of its supercomputer Colossus, the which contains 1 million GPUs. Anthropic has a contract of $1.25 billion per month with SpaceXAI to buy all the compute capacity at Colossus 1 data center. === Criticism and policy === Increasing, promoting or constraining progress in artificial intelligence has often be done via controlling the amount of compute. Policymarkers have enacted policies and provided support to make compute resources more accessible to domestic AI researchers. In a January 2022 report, the Center for Security and Emerging Technology (CSET) suggested to institutions that increasingly powerful and generalizable AI (AGI) will likely require other strategies than maximizing compute. Some AI researchers are also concerned that government might exclusively focus on scaling compute instead of other strategies. The CSET has reported on the various bottlenecks which could explain why deep learning needs for compute have slow down: training is expensive and training extremely large models generates traffic jams across many processors that are difficult to manage. there is a limited supply of AI chips (see AI chip memory shortage). CSET advances that the main resource is human capital, specifically talented researchers — according to a 2023 published survey of more than 400 AI researchers, academic and private sector workers. The survey found that AI researchers are not primarily or exclusively constrained by compute access. However, both academic and industry AI researchers equally report concerns that insufficient compute could prevent them from contributing meaningfully to AI research in the future. High compute users are more concerned about compute access. When asked about which resource provided by the government would be the most useful to them, some AI researchers select compute, other prefer grant funding. For this goal, CSET advised policymakers to ensure that even researchers with smaller budgets could effectively contribute to AI research. Other proposed strategies include using contemporary AI algorithms, managing modern AI infrastructure or focusing on interdisciplinary work between the AI field and other fields of computer science. A 2024 study on compute access found that academic-only AI research teams often have less compute intensive research topics, especially foundation models, compared to industry AI labs. As a consequence, academia is likely to play a smaller role in advancing such techniques. The researchers suggest nationally-sponsored computing infrastructure as well as open science initiatives to boost academic compute access. === Data === A 2022 study found that current large language models are significantly under-trained, a consequence of focusing on scaling language models whilst keeping the amount of training data constant. By training over 400 language models of various parameter and token size, they found that "for compute-optimal training", the model size and the number of training tokens should ideally be scaled equally: for every doubling of model size the number of training tokens should also be doubled.
Text normalization
Text normalization is the process of transforming text into a single canonical form that it might not have had before. Normalizing text before storing or processing it allows for separation of concerns, since input is guaranteed to be consistent before operations are performed on it. Text normalization requires being aware of what type of text is to be normalized and how it is to be processed afterwards; there is no all-purpose normalization procedure. == Applications == Text normalization is frequently used when converting text to speech. Numbers, dates, acronyms, and abbreviations are non-standard "words" that need to be pronounced differently depending on context. For example: "$200" would be pronounced as "two hundred dollars" in English, but as "lua selau tālā" in Samoan. "vi" could be pronounced as "vie," "vee," or "the sixth" depending on the surrounding words. Text can also be normalized for storing and searching in a database. For instance, if a search for "resume" is to match the word "résumé," then the text would be normalized by removing diacritical marks; and if "john" is to match "John", the text would be converted to a single case. To prepare text for searching, it might also be stemmed (e.g. converting "flew" and "flying" both into "fly"), canonicalized (e.g. consistently using American or British English spelling), or have stop words removed. == Techniques == For simple, context-independent normalization, such as removing non-alphanumeric characters or diacritical marks, regular expressions would suffice. For example, the sed script sed ‑e "s/\s+/ /g" inputfile would normalize runs of whitespace characters into a single space. More complex normalization requires correspondingly complicated algorithms, including domain knowledge of the language and vocabulary being normalized. Among other approaches, text normalization has been modeled as a problem of tokenizing and tagging streams of text and as a special case of machine translation. == Textual scholarship == In the field of textual scholarship and the editing of historic texts, the term "normalization" implies a degree of modernization and standardization – for example in the extension of scribal abbreviations and the transliteration of the archaic glyphs typically found in manuscript and early printed sources. A normalized edition is therefore distinguished from a diplomatic edition (or semi-diplomatic edition), in which some attempt is made to preserve these features. The aim is to strike an appropriate balance between, on the one hand, rigorous fidelity to the source text (including, for example, the preservation of enigmatic and ambiguous elements); and, on the other, producing a new text that will be comprehensible and accessible to the modern reader. The extent of normalization is therefore at the discretion of the editor, and will vary. Some editors, for example, choose to modernize archaic spellings and punctuation, but others do not. An edition of a text might be normalized based on internal criteria, where orthography is standardized according to the language of the original, or external criteria, where the norms of a different time period are applied. For an example of the latter, a published edition of a medieval Icelandic manuscript might be normalized to the conventions of modern Icelandic, or it might be normalized to Classical Old Icelandic. Standards of normalization vary based on language of the edition as well as the specific conventions of the publisher.
Legal expert system
A legal expert system is a domain-specific expert system that uses artificial intelligence to emulate the decision-making abilities of a human expert in the field of law. Legal expert systems employ a rule base or knowledge base and an inference engine to accumulate, reference and produce expert knowledge on specific subjects within the legal domain. == Purpose == It has been suggested that legal expert systems could help to manage the rapid expansion of legal information and decisions that began to intensify in the late 1960s. Many of the first legal expert systems were created in the 1970s and 1980s. Lawyers were originally identified as primary target users of legal expert systems. Potential motivations for this work included: quicker delivery of legal advice; reduced time spent in repetitive, labour-intensive legal tasks; development of knowledge management techniques that were not dependent on staff; reduced overhead and labour costs and higher profitability for law firms; and reduced fees for clients. Some early development work was oriented toward the creation of automated judges. One of the first use cases was the encoding of the British Nationality Act at Imperial College carried out under the supervision of Marek Sergot and Robert Kowalski. Lance Elliot wrote: "The British Nationality Act was passed in 1981 and shortly thereafter was used as a means of showcasing the efficacy of using Artificial Intelligence (AI) techniques and technologies, doing so to explore how the at-the-time newly enacted statutory law might be encoded into a computerized logic-based formalization." The authors’ seminal article, "The British Nationality Act as a Logic Program," published in 1986 in the Communications of the ACM journal, is one of the first and best-known works in computational law, and one of the most widely cited papers in the field. In 2021, the Inaugural CodeX Prize was awarded to Robert Kowalski, Fariba Sadri, and Marek Sergot in acknowledgment of their groundbreaking work on the application of logic programming to the formalization and analysis of the British Nationality Act. Later work on legal expert systems has identified potential benefits to non-lawyers as a means to increase access to legal knowledge. Legal expert systems can also support administrative processes, facilitate decision-making processes, automate rule-based analyses, and exchange information directly with citizen-users. == Types == === Architectural variations === Rule-based expert systems rely on a model of deductive reasoning that utilizes "If A, then B" rules. In a rule-based legal expert system, information is represented in the form of deductive rules within the knowledge base. In rule-based legal expert systems, logic programming has historically been applied to automate complex compliance paperwork. A notable early example designed for high-volume regulatory filings was the 1999 Intelligent Filing Manager (INTELLIFM), which utilized Prolog rules as its core inference engine to automate the generation, publishing, and population of structured forms via distributed COM interfaces. Case-based reasoning models, which store and manipulate examples or cases, hold the potential to emulate an analogical reasoning process thought to be well-suited for the legal domain. This model effectively draws on known experiences our outcomes for similar problems. A neural net relies on a computer model that mimics that structure of a human brain, and operates in a very similar way to the case-based reasoning model. This expert system model is capable of recognizing and classifying patterns within the realm of legal knowledge and dealing with imprecise inputs. Fuzzy logic models attempt to create 'fuzzy' concepts or objects that can then be converted into quantitative terms or rules that are indexed and retrieved by the system. In the legal domain, fuzzy logic can be used for rule-based and case-based reasoning models. === Theoretical variations === Some legal expert system architects have adopted a very practical approach, employing scientific modes of reasoning within a given set of rules or cases. Others have opted for a broader philosophical approach inspired by jurisprudential reasoning modes emanating from established legal theoreticians. === Functional variations === Some legal expert systems aim to arrive at a particular conclusion in law, while others are designed to predict a particular outcome. An example of a predictive system is one that predicts the outcome of judicial decisions, the value of a case, or the outcome of litigation. == Reception == Many forms of legal expert systems have become widely used and accepted by both the legal community and the users of legal services. == Challenges == === Domain-related problems === The inherent complexity of law as a discipline raises immediate challenges for legal expert system knowledge engineers. Legal matters often involve interrelated facts and issues, which further compound the complexity. Factual uncertainty may also arise when there are disputed versions of factual representations that must be input into an expert system to begin the reasoning process. === Computerized problem solving === The limitations of most computerized problem solving techniques inhibit the success of many expert systems in the legal domain. Expert systems typically rely on deductive reasoning models that have difficulty according degrees of weight to certain principles of law or importance to previously decided cases that may or may not influence a decision in an immediate case or context. === Representation of legal knowledge === Expert legal knowledge can be difficult to represent or formalize within the structure of an expert system. For knowledge engineers, challenges include: Open texture: Law is rarely applied in an exact way to specific facts, and exact outcomes are rarely a certainty. Statutes may be interpreted according to different linguistic interpretations, reliance on precedent cases or other contextual factors including a particular judge's conception of fairness. The balancing of reasons: Many arguments involve considerations or reasons that are not easily represented in a logical way. For instance, many constitutional legal issues are said to balance independently well-established considerations for state interests against individual rights. Such balancing may draw on extra-legal considerations that would be difficult to represent logically in an expert system. Indeterminacy of legal reasoning: In the adversarial arena of law, it is common to have two strong arguments on a single point. Determining the 'right' answer may depend on a majority vote among expert judges, as in the case of an appeal. === Time and cost effectiveness === Creating a functioning expert system requires significant investments in software architecture, subject matter expertise and knowledge engineering. Faced with these challenges, many system architects restrict the domain in terms of subject matter and jurisdiction. The consequence of this approach is the creation of narrowly focused and geographically restricted legal expert systems that are difficult to justify on a cost-benefit basis. Current applications of AI in the legal field utilize machines to review documents, particularly when a high level of completeness and confidence in the quality of document analysis is depended upon, such as in instances of litigation and where due diligence play a role. Among the numerically most quantifiable advantages of AI in the legal field are the time and money saving impact by freeing lawyers from having to spend inordinate amounts of their valuable time on routine tasks, aiding in setting free lawyers’ creative energy by reducing stress. This in turn increases the rate of case load reduction by accomplishing better results in less time, which unlocks potential additional revenue per unit of time spend on a case. The cost of setting up and maintaining AI systems in law is more than offset by the attained savings through increased efficacy; unbalanced cost can be assigned to clients. === Lack of correctness in results or decisions === Legal expert systems may lead non-expert users to incorrect or inaccurate results and decisions. This problem could be compounded by the fact that users may rely heavily on the correctness or trustworthiness of results or decisions generated by these systems. == Examples == ASHSD-II is a hybrid legal expert system that blends rule-based and case-based reasoning models in the area of matrimonial property disputes under English law. CHIRON is a hybrid legal expert system that blends rule-based and case-based reasoning models to support tax planning activities under United States tax law and codes. JUDGE is a rule-based legal expert system that deals with sentencing in the criminal legal domain for offences relating to murder, assault and manslaughter. Legislate is a knowledge graph powered contract management platform whi
Tip and cue
Tip and cue, sometimes referred to as tip and que, tipping and cueing, or tipping and queing, is a method for satellite imagery and reconnaissance satellites to automatically coordinate tracking of objects across different satellites in real or near real-time. This technique ensures continuous tracking of targets as they move across different regions by handing them off between satellites, sharing satellite imagery and collateral across discrete satellites. The coordination between various satellites and their complementary sensors allows for more accurate and efficient data collection. This system is particularly useful in scenarios requiring real-time monitoring and rapid response; the method significantly improves situational awareness and operational effectiveness. Tip and cue techniques involve integrating various sensor systems, each playing a specific role in the tracking process. As a target moves, it is handed off from one satellite to another, ensuring continuous monitoring. This coordination optimizes data collection and analysis, enhancing overall tracking accuracy. The real-time information gathered by these satellites is critical for decision-making in various applications, including defense and surveillance. By leveraging multiple satellites and their sensors, it provides broader coverage and more reliable tracking, and the continuous handoff between satellites ensures there are no gaps in monitoring, essential for high-stakes applications. The real-time data provided by this system allows for timely and informed decisions, improving response times and outcomes. Tip and cue methodologies are a part of geospatial intelligence, or GEOINT. Robert Cardillo, a former director of the National Geospatial-Intelligence Agency, highlighted the importance of tip and cue methods to their data collection efforts in 2015. == Historical Development == The concept of tip and cue in satellite monitoring has its origins in early military applications designed to enhance missile detection and tracking systems. During the Cold War, advancements in infrared sensing technologies laid the groundwork for more sophisticated tip and cue techniques. The integration of different sensor types, such as radar and optical sensors, in the 1990s expanded the capabilities of tip and cue systems beyond military applications. These advancements have made tip and cue techniques essential for various civilian uses, including disaster monitoring and environmental surveillance. Significant progress was made with the advent of high-speed data processing and communication technologies in the early 2000s, further refining the method. Advanced algorithms and data fusion techniques have been introduced to better integrate information from multiple sensors. Machine learning technologies now play a crucial role in improving detection and prediction capabilities, allowing for more adaptive and efficient tracking. Richmond and Brennan of Lockheed Martin, presenting to the annual technical conference of the Maui Space Surveillance Complex (formerly the Air Force Maui Optical Station (AMOS)), discussed the algorithms needed for 'tip and cue', to facilitate "multi-phenomenology data fusion." The Space Surveillance Telescope (SST) at Naval Communication Station Harold E. Holt in Australia, operated by the United States Space Force and designed by the Massachusetts Institute of Technology Lincoln Laboratory, was reported by the Defense Advanced Research Projects Agency (DARPA) to be a leader in creating and improving tip and cue techniques, from a large library of orbital object data. == Technical overview == Tip and cue systems utilize a network of at least two satellites equipped with complementary sensor technologies to track moving objects in real-time. The method involves detecting a target with a primary sensor, such as an infrared or photographic sensor, which then cues secondary sensors on the same or other satellites for more detailed monitoring. This handoff process between discrete systems ensures continuous tracking as the target moves across different areas, leveraging each systems strengths. Data collected by these systems and sensors are rapidly processed and shared among the network, enhancing situational awareness. This coordination optimizes resource usage and improves the accuracy of tracking moving objects over large areas. The primary sensors detect initial targets based on specific signatures, such as heat or movement, and then cue secondary sensors to gather more precise data. This ensures that each sensor operates within its optimal range, maintaining high tracking accuracy and reliability. The integration of various sensor types, including optical, radar, and infrared, allows the system to function effectively under different conditions and environments. Real-time data processing and communication between satellites and ground stations are crucial for timely and accurate target tracking. Satellites using tip and cue processes may use either passive or active scanning methodoloigies. These systems may also leverage both orbital and ground-based ELINT (electronic signals intelligence). == Known use cases == Tip and cue systems have been extensively utilized in military applications, particularly for missile detection and defense. These systems enable early detection of missile launches using infrared sensors, which then cue other sensors to track the missile's trajectory more accurately. In environmental monitoring, tip and cue techniques help track natural disasters such as wildfires and hurricanes by coordinating various satellite sensors for comprehensive data collection and analysis. Surveillance and reconnaissance operations also benefit from tip and cue systems, which provide continuous and precise tracking of moving objects, enhancing situational awareness. Additionally, these systems are used in maritime surveillance to monitor ship movements and detect illegal activities such as smuggling and piracy. Tip and cue systems are used in disaster management. For instance, during wildfires, infrared sensors can detect heat signatures, prompting other sensors to gather detailed imagery and data on fire spread and intensity. This coordinated approach allows for real-time monitoring and rapid response, crucial for mitigating damage and saving lives. Similarly, in hurricane tracking, satellites equipped with various sensors can monitor storm development and progression, providing timely information for emergency management agencies. The integration of multiple sensor types ensures accurate and comprehensive coverage of these dynamic and fast-changing events. In maritime surveillance, or maritime domain awareness (MDA), tip and cue systems enhance the detection and monitoring of vessel movements, contributing to maritime security. By coordinating satellite sensors, these systems can track ships over vast ocean areas, identifying potential threats or illegal activities such as smuggling, piracy, and illegal fishing. The ability to maintain continuous surveillance and share data in real-time with maritime authorities improves response times and enforcement capabilities. This application of tip and cue systems not only aids in law enforcement but also supports environmental conservation efforts by monitoring protected marine areas. Automatic Identification System (AIS) is one of the most important sources of data for the MDA agencies. AIS is used in order for ships to know each other's whereabouts, they transmit a signal from ship to ship and to shore. Lately, the system has been developed into satellite system, so called satellite AIS, which makes the system more effective. All ocean-going vessels above 300 tons, are supposed to use and transmit via AIS according to the International Maritime Organization. The satellite constellations help facilitate this with tip and cue methodologies.
Dartmouth workshop
The Dartmouth Summer Research Project on Artificial Intelligence was a 1956 summer workshop widely considered to be the founding event of artificial intelligence as a field. The workshop has been referred to as "the Constitutional Convention of AI". The project's four organizers, Claude Shannon, John McCarthy, Nathaniel Rochester and Marvin Minsky, are considered some of the "founding fathers" of AI. However it was not the first conference devoted to what would now be described as the question of artificial intelligence: it postdated meetings such as the 1951 Paris cybernetics conference and the Macy meetings. The project lasted approximately six to eight weeks and consisted largely of brainstorming sessions. Eleven mathematicians and scientists originally planned to attend; not all of them attended, but more than ten others came for short times. == Background == In the early 1950s, there were various names for the field of "thinking machines": cybernetics, automata theory, and complex information processing. The variety of names suggests the variety of conceptual orientations. In 1955, John McCarthy, then a young Assistant Professor of Mathematics at Dartmouth College, decided to organize a group to clarify and develop ideas about thinking machines. He picked the name 'Artificial Intelligence' for the new field. He chose the name partly for its neutrality; avoiding a focus on narrow automata theory, and avoiding cybernetics which was heavily focused on analog feedback, as well as him potentially having to accept the assertive Norbert Wiener as guru or having to argue with him. In early 1955, McCarthy approached the Rockefeller Foundation to request funding for a summer seminar at Dartmouth for about 10 participants. In June, he and Claude Shannon, a founder of information theory then at Bell Labs, met with Robert Morison, Director of Biological and Medical Research to discuss the idea and possible funding, though Morison was unsure whether money would be made available for such a visionary project. On September 2, 1955, the project was formally proposed by McCarthy, Marvin Minsky, Nathaniel Rochester and Claude Shannon. The proposal is credited with introducing the term 'artificial intelligence'. The Proposal states: We propose that a 2-month, 10-man study of artificial intelligence be carried out during the summer of 1956 at Dartmouth College in Hanover, New Hampshire. The study is to proceed on the basis of the conjecture that every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. An attempt will be made to find how to make machines use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves. We think that a significant advance can be made in one or more of these problems if a carefully selected group of scientists work on it together for a summer. The proposal goes on to discuss computers, natural language processing, neural networks, theory of computation, abstraction and creativity (these areas within the field of artificial intelligence are considered still relevant to the work of the field). On May 26, 1956, McCarthy notified Robert Morison of the planned 11 attendees: For the full period: 1) Dr. Marvin Minsky 2) Dr. Julian Bigelow 3) Professor D.M. Mackay 4) Mr. Ray Solomonoff 5) Mr. John Holland 6) Dr. John McCarthy For four weeks: 7) Dr. Claude Shannon 8) Mr. Nathaniel Rochester 9) Mr. Oliver Selfridge For the first two weeks: 10) Dr. Allen Newell 11) Professor Herbert Simon He noted, "we will concentrate on a problem of devising a way of programming a calculator to form concepts and to form generalizations. This of course is subject to change when the group gets together." The actual participants came at different times, mostly for much shorter times. Trenchard More replaced Rochester for three weeks and MacKay and Holland did not attend—but the project was set to begin. Around June 18, 1956, the earliest participants (perhaps only Ray Solomonoff, maybe with Tom Etter) arrived at the Dartmouth campus in Hanover, N.H., to join John McCarthy who already had an apartment there. Solomonoff and Minsky stayed at Professors' apartments, but most would stay at the Hanover Inn. == Dates == The Dartmouth Workshop is usually said to have run for six weeks. Ray Solomonoff's notes taken during the workshop, however, indicate that it ran for roughly eight weeks, from about June 18 to August 17. Solomonoff's notes start on June 22; June 28 mentions Minsky, June 30 mentions Hanover, N.H., July 1 mentions Tom Etter. On August 17, Solomonoff gave a final talk. == Participants == Initially, McCarthy lost his list of attendees. Instead, after the workshop, McCarthy sent Solomonoff a preliminary list of participants and visitors plus those interested in the subject. 47 people were listed. Solomonoff, however, made a list of participants in his notes of the summer project: Ray Solomonoff Marvin Minsky John McCarthy Claude Shannon Trenchard More Nat Rochester Oliver Selfridge Julian Bigelow W. Ross Ashby W.S. McCulloch Abraham Robinson Tom Etter John Nash David Sayre Arthur Samuel Kenneth R. Shoulders Shoulders' friend Alex Bernstein Herbert Simon Allen Newell Shannon attended Solomonoff's talk on July 10 and Bigelow gave a talk on August 15. Solomonoff doesn't mention Bernard Widrow, but in 1994 Widrow said that he and an unidentified colleague from the same lab in MIT had attended for one week. In the same interview Widrow recalled that "I think [Wesley] Clark and [Belmont] Farley were there from Lincoln Lab." Trenchard mentions R. Culver and Solomonoff mentions Bill Shutz. Herb Gelernter didn't attend, but was influenced later by what Rochester learned. In an article in IEEE Spectrum, Grace Solomonoff additionally identifies Peter Milner in a photo taken by Nathaniel Rochester in front of Dartmouth Hall. Ray Solomonoff, Marvin Minsky, and John McCarthy were the only three who stayed for the full time. Trenchard took attendance during two weeks of his three-week visit. From three to about eight people would attend the daily sessions. == Event and aftermath == They had the entire top floor of the Dartmouth Math Department to themselves, and most weekdays they would meet at the main math classroom where someone might lead a discussion focusing on his ideas, or more frequently, a general discussion would be held. It was not a directed group research project; discussions covered many topics, but several directions are considered to have been initiated or encouraged by the Workshop: the rise of symbolic methods, systems focused on limited domains (early expert systems), and deductive systems versus inductive systems. One participant, Arthur Samuel, said, "It was very interesting, very stimulating, very exciting". Ray Solomonoff kept notes giving his impression of the talks and the ideas from various discussions. === McCarthy's 1956 AI distribution list === This is the list in the "People Interested in the Artificial Intelligence Problem" document which McCarthy produced in 1956, partly in lieu of a list of attendees at the Dartmouth workshop. According to McCarthy the list was "being sent to the people on the list and a few others", and its purpose was "to let those on it know who is interested in receiving documents on the problem" of artificial intelligence. McCarthy also promised to deliver them a report on the Dartmouth conference, and to send an updated list soon afterwards. It includes people who did not attend the conference and does not include everyone who did attend it.
List of assembly software and tools
This is a list of assembly software and tools, including software used for assembly language programming, machine code generation, disassembly, debugging, binary analysis, reverse engineering, and instruction-set simulation. == Assemblers and machine-code generators == == Disassemblers and binary-analysis tools == == Debuggers with assembly-level features == == Educational IDEs, simulators and emulators == == Portable and intermediate assembly-like languages == == Assembly language families == Assembly language is not a single programming language, but a family of low-level languages associated with particular instruction set architectures and processor families. Examples include:
Sugeno integral
In mathematics, the Sugeno integral, introduced by Michio Sugeno as a fuzzy integral in work on fuzzy measures at the Tokyo Institute of Technology, is a type of integral with respect to a fuzzy measure. Let ( X , Ω ) {\displaystyle (X,\Omega )} be a measurable space and let h : X → [ 0 , 1 ] {\displaystyle h:X\to [0,1]} be an Ω {\displaystyle \Omega } -measurable function. The Sugeno integral over the crisp set A ⊆ X {\displaystyle A\subseteq X} of the function h {\displaystyle h} with respect to the fuzzy measure g {\displaystyle g} is defined by: ∫ A h ( x ) ∘ g = sup E ⊆ X [ min ( min x ∈ E h ( x ) , g ( A ∩ E ) ) ] = sup α ∈ [ 0 , 1 ] [ min ( α , g ( A ∩ F α ) ) ] {\displaystyle \int _{A}h(x)\circ g={\sup _{E\subseteq X}}\left[\min \left(\min _{x\in E}h(x),g(A\cap E)\right)\right]={\sup _{\alpha \in [0,1]}}\left[\min \left(\alpha ,g(A\cap F_{\alpha })\right)\right]} where F α = { x | h ( x ) ≥ α } {\displaystyle F_{\alpha }=\left\{x|h(x)\geq \alpha \right\}} . The Sugeno integral over the fuzzy set A ~ {\displaystyle {\tilde {A}}} of the function h {\displaystyle h} with respect to the fuzzy measure g {\displaystyle g} is defined by: ∫ A h ( x ) ∘ g = ∫ X [ h A ( x ) ∧ h ( x ) ] ∘ g {\displaystyle \int _{A}h(x)\circ g=\int _{X}\left[h_{A}(x)\wedge h(x)\right]\circ g} where h A ( x ) {\displaystyle h_{A}(x)} is the membership function of the fuzzy set A ~ {\displaystyle {\tilde {A}}} . == Usage and Relationships == Sugeno integral is related to h-index.