In cryptography and the theory of computation, Yao's test is a test defined by Andrew Chi-Chih Yao in 1982, against pseudo-random sequences. A sequence of words passes Yao's test if an attacker with reasonable computational power cannot distinguish it from a sequence generated uniformly at random. == Formal statement == === Boolean circuits === Let P {\displaystyle P} be a polynomial, and S = { S k } k {\displaystyle S=\{S_{k}\}_{k}} be a collection of sets S k {\displaystyle S_{k}} of P ( k ) {\displaystyle P(k)} -bit long sequences, and for each k {\displaystyle k} , let μ k {\displaystyle \mu _{k}} be a probability distribution on S k {\displaystyle S_{k}} , and P C {\displaystyle P_{C}} be a polynomial. A predicting collection C = { C k } {\displaystyle C=\{C_{k}\}} is a collection of boolean circuits of size less than P C ( k ) {\displaystyle P_{C}(k)} . Let p k , S C {\displaystyle p_{k,S}^{C}} be the probability that on input s {\displaystyle s} , a string randomly selected in S k {\displaystyle S_{k}} with probability μ ( s ) {\displaystyle \mu (s)} , C k ( s ) = 1 {\displaystyle C_{k}(s)=1} , i.e. Moreover, let p k , U C {\displaystyle p_{k,U}^{C}} be the probability that C k ( s ) = 1 {\displaystyle C_{k}(s)=1} on input s {\displaystyle s} a P ( k ) {\displaystyle P(k)} -bit long sequence selected uniformly at random in { 0 , 1 } P ( k ) {\displaystyle \{0,1\}^{P(k)}} . We say that S {\displaystyle S} passes Yao's test if for all predicting collection C {\displaystyle C} , for all but finitely many k {\displaystyle k} , for all polynomial Q {\displaystyle Q} : === Probabilistic formulation === As in the case of the next-bit test, the predicting collection used in the above definition can be replaced by a probabilistic Turing machine, working in polynomial time. This also yields a strictly stronger definition of Yao's test (see Adleman's theorem). Indeed, one could decide undecidable properties of the pseudo-random sequence with the non-uniform circuits described above, whereas BPP machines can always be simulated by exponential-time deterministic Turing machines.
Iterative reconstruction
Iterative reconstruction refers to iterative algorithms used to reconstruct 2D and 3D images in certain imaging techniques. For example, in computed tomography an image must be reconstructed from projections of an object. Here, iterative reconstruction techniques are usually a better, but computationally more expensive alternative to the common filtered back projection (FBP) method, which directly calculates the image in a single reconstruction step. In recent research works, scientists have shown that extremely fast computations and massive parallelism is possible for iterative reconstruction, which makes iterative reconstruction practical for commercialization. == Basic concepts == The reconstruction of an image from the acquired data is an inverse problem. Often, it is not possible to exactly solve the inverse problem directly. In this case, a direct algorithm has to approximate the solution, which might cause visible reconstruction artifacts in the image. Iterative algorithms approach the correct solution using multiple iteration steps, which allows to obtain a better reconstruction at the cost of a higher computation time. There are a large variety of algorithms, but each starts with an assumed image, computes projections from the image, compares the original projection data and updates the image based upon the difference between the calculated and the actual projections. === Algebraic reconstruction === The Algebraic Reconstruction Technique (ART) was the first iterative reconstruction technique used for computed tomography by Hounsfield. === Iterative Sparse Asymptotic Minimum Variance === The iterative sparse asymptotic minimum variance algorithm is an iterative, parameter-free superresolution tomographic reconstruction method inspired by compressed sensing, with applications in synthetic-aperture radar, computed tomography scan, and magnetic resonance imaging (MRI). === Statistical reconstruction === There are typically five components to statistical iterative image reconstruction algorithms, e.g. An object model that expresses the unknown continuous-space function f ( r ) {\displaystyle f(r)} that is to be reconstructed in terms of a finite series with unknown coefficients that must be estimated from the data. A system model that relates the unknown object to the "ideal" measurements that would be recorded in the absence of measurement noise. Often this is a linear model of the form A x + ϵ {\displaystyle \mathbf {A} x+\epsilon } , where ϵ {\displaystyle \epsilon } represents the noise. A statistical model that describes how the noisy measurements vary around their ideal values. Often Gaussian noise or Poisson statistics are assumed. Because Poisson statistics are closer to reality, it is more widely used. A cost function that is to be minimized to estimate the image coefficient vector. Often this cost function includes some form of regularization. Sometimes the regularization is based on Markov random fields. An algorithm, usually iterative, for minimizing the cost function, including some initial estimate of the image and some stopping criterion for terminating the iterations. === Learned Iterative Reconstruction === In learned iterative reconstruction, the updating algorithm is learned from training data using techniques from machine learning such as convolutional neural networks, while still incorporating the image formation model. This typically gives faster and higher quality reconstructions and has been applied to CT and MRI reconstruction. == Advantages == The advantages of the iterative approach include improved insensitivity to noise and capability of reconstructing an optimal image in the case of incomplete data. The method has been applied in emission tomography modalities like SPECT and PET, where there is significant attenuation along ray paths and noise statistics are relatively poor. Statistical, likelihood-based approaches: Statistical, likelihood-based iterative expectation-maximization algorithms are now the preferred method of reconstruction. Such algorithms compute estimates of the likely distribution of annihilation events that led to the measured data, based on statistical principle, often providing better noise profiles and resistance to the streak artifacts common with FBP. Since the density of radioactive tracer is a function in a function space, therefore of extremely high-dimensions, methods which regularize the maximum-likelihood solution turning it towards penalized or maximum a-posteriori methods can have significant advantages for low counts. Examples such as Ulf Grenander's Sieve estimator or Bayes penalty methods, or via I.J. Good's roughness method may yield superior performance to expectation-maximization-based methods which involve a Poisson likelihood function only. As another example, it is considered superior when one does not have a large set of projections available, when the projections are not distributed uniformly in angle, or when the projections are sparse or missing at certain orientations. These scenarios may occur in intraoperative CT, in cardiac CT, or when metal artifacts require the exclusion of some portions of the projection data. In Magnetic Resonance Imaging it can be used to reconstruct images from data acquired with multiple receive coils and with sampling patterns different from the conventional Cartesian grid and allows the use of improved regularization techniques (e.g. total variation) or an extended modeling of physical processes to improve the reconstruction. For example, with iterative algorithms it is possible to reconstruct images from data acquired in a very short time as required for real-time MRI (rt-MRI). In Cryo Electron Tomography, where the limited number of projections are acquired due to the hardware limitations and to avoid the biological specimen damage, it can be used along with compressive sensing techniques or regularization functions (e.g. Huber function) to improve the reconstruction for better interpretation. Here is an example that illustrates the benefits of iterative image reconstruction for cardiac MRI.
Megami Tensei
Megami Tensei, marketed internationally as Shin Megami Tensei (formerly Revelations), is a Japanese media franchise created by Aya Nishitani, Kouji "Cozy" Okada, Ginichiro Suzuki, and Kazunari Suzuki. Primarily developed and published by Atlus, the franchise consists of multiple subseries and covers multiple role-playing video game genres including tactical role-playing, action role-playing, and massively multiplayer online role-playing. The first two titles in the series were published by Namco (now Bandai Namco Entertainment), but have been almost always published by Atlus in Japan and North America since the release of Shin Megami Tensei. For Europe, Atlus publishes the games through third-party companies. The series was originally based on Digital Devil Story, a science fiction novel series by Aya Nishitani. The series takes its name from the first book's subtitle. Most Megami Tensei titles are stand-alone entries with their own stories and characters. Recurring elements include plot themes, a story shaped by the player's choices, and the ability to fight using and often recruit creatures (demons, Personas) to aid the player in battle. Elements of philosophy, religion, occultism, and science fiction have all been incorporated into the series at different times. While not maintaining as high a profile as series such as Final Fantasy and Dragon Quest, it is highly popular in Japan and maintains a strong cult following in the West, finding critical and commercial success. The series has become well known for its artistic direction, challenging gameplay, and music, but raised controversy over its mature content, dark themes, and use of Christian religious imagery. Additional media include manga adaptations, anime films, and television series. In Japan, some games in the series do not use the "Megami Tensei" title, such as the Persona sub-series. Many of the early games in the series were not localized due to potentially controversial content including religious references, and later due to their age. English localizations have used the "Shin Megami Tensei" moniker since the release of Shin Megami Tensei: Nocturne in 2004. == Titles == === Games === The first installment in the franchise, Digital Devil Story: Megami Tensei, was released on September 11, 1987. The following entries have nearly always been unrelated to each other except in carrying over thematic and gameplay elements. The Megami Tensei games, and the later Shin Megami Tensei titles form the core of the series, while other subseries such as Persona, Devil Children, and Devil Summoner are spin-offs marketed as part of the franchise. There are also stand-alone spin-off titles. ==== Main series ==== Two entries were released for the Famicom: Digital Devil Story: Megami Tensei in 1987, and Digital Devil Story: Megami Tensei II in 1990. The two titles are unrelated to each other in terms of story, and each introduced the basic gameplay and story mechanics that would come to define the series. Three entries were released for the Super Famicom: Shin Megami Tensei in 1992, followed byShin Megami Tensei II in 1994, and Shin Megami Tensei If..., released later in the same year. Shin Megami Tensei III: Nocturne was released in 2003 for the PlayStation 2. Its Maniax Edition director's cut was released in Japan and North America in 2004, and in Europe in 2005. The numeral was dropped for its North American release, and its title changed to Shin Megami Tensei: Lucifer's Call in Europe. Shin Megami Tensei IV for the Nintendo 3DS was released in 2013 in Japan and North America, and a year later in Europe as a digital-only release. Another game set in the same universe, Shin Megami Tensei IV: Apocalypse, was released for the 3DS in February 2016 in Japan. Shin Megami Tensei V was released on the Nintendo Switch in 2021. An enhanced version of the game titled Shin Megami Tensei V: Vengeance was released in June 2024 for Microsoft Windows, Nintendo Switch, PlayStation 4, PlayStation 5, Xbox One and Xbox Series X/S. In addition to the main series, there are also numerous spin-offs. Shin Megami Tensei: Nine, was released for the Xbox in 2002. Originally designed as a massively multiplayer online role-playing game (MMORPG), it was later split into a dual single-player and multiplayer package, and the single-player version released first. The online version was delayed and eventually cancelled as the developers could not manage the required online capacities using Xbox Live. Shin Megami Tensei: Imagine, a true MMOROG released for Microsoft Windows, was released in 2007 in Japan, 2008 in North America, and 2009 in Europe. Western service was terminated in 2014 when Marvelous USA, the game's then-handlers, shut down their PC Online game department. Shin Megami Tensei: Strange Journey was released for the Nintendo DS in 2009 in Japan and 2010 in North America. Its Japanese service ended in May 2016. A smartphone game, Shin Megami Tensei: Liberation Dx2, was released in 2018. ==== Persona ==== The Persona series is the largest and most popular spin-off from the Megami Tensei series. The first entry in the series, Megami Ibunroku Persona (originally released overseas as Revelations: Persona), was released in 1996 in Japan and North America. The first Persona 2 title, Innocent Sin, was released in 1999 in Japan. The second game, Eternal Punishment, was released in 2000 in Japan and North America. Persona 3 was released in 2006 in Japan, 2007 in North America, and 2008 in Europe. Its sequel, Persona 4, was released in 2008 in Japan and North America, and in 2009 in Europe. A sixth entry in the series, Persona 5, was released in Japan on September 15, 2016, and was released in North America and Europe on April 4, 2017, to critical acclaim. The series also features spin-offs, including Persona Q: Shadow of the Labyrinth and Persona Q2: New Cinema Labyrinth, two fighting games Persona 4 Arena and its sequel Arena Ultimax as well as the crossover fighting game BlazBlue: Cross Tag Battle, tactical role-playing game Persona 5 Tactica, action role-playing game Persona 5 Strikers and rhythm games Persona 4: Dancing All Night, Persona 3: Dancing in Moonlight, and Persona 5: Dancing in Starlight. While Persona 3 and 4 used the Shin Megami Tensei moniker in the West, it was dropped for the Persona 4 Arena duology and Persona 4 Golden as it would have made the titles too long to be practical. ==== Devil Summoner ==== The Devil Summoner subseries began in 1995 with the release of Shin Megami Tensei: Devil Summoner. It was followed by Devil Summoner: Soul Hackers in 1997, then followed by Soul Hackers 2, released in 2022. Two action role-playing prequels set in 1920s Tokyo were also developed, which revolve around demon summoner Raidou Kuzunoha: Raidou Kuzunoha vs. the Soulless Army was released in 2006, and Raidou Kuzunoha vs. King Abaddon was released in 2008. ==== Other spin-offs ==== Aside from Persona and Devil Summoner, there are other spin-off series covering multiple genres. After the release of Shin Megami Tensei II, Atlus began focusing work on building spin-offs and subseries that would form part of the Megami Tensei franchise. Shortly after Nocturne's release, a duology titled Digital Devil Saga (Digital Devil Saga: Avatar Tuner in Japan) was created based around similar systems to Nocturne, and was also intended as a more accessible gaming experience. Two tactical role-playing games have been developed by Atlus for the DS under the Devil Survivor moniker: the original Devil Survivor and Devil Survivor 2. Both have received expanded ports for the 3DS. Other subseries include Last Bible, a series aimed at a younger audience and using a pure fantasy setting; Devil Children, which was inspired by the popular Pokémon series; and Majin Tensei, a series of strategy games. Two notable stand-alone spin-offs are action spin-off Jack Bros. and Tokyo Mirage Sessions ♯FE, a crossover with Intelligent Systems' Fire Emblem series. === Related media === Several titles in the franchise have received anime and manga adaptations. Persona 3 received both a four-part theatrical adaptation (#1 Spring of Birth, #2 Midsummer Knight's Dream, #3 Falling Down, #4 Winter of Rebirth), and a spin-off series titled Persona: Trinity Soul. Persona 4 received two adaptations: Persona 4: The Animation, based on the original game, and Persona 4: The Golden Animation, based on its expanded PlayStation Vita port. A live-action television series based on the original Devil Summoner was broadcast between 1997 and 1998. Devil Survivor 2 also received an anime adaptation of the same name, and the Devil Children series received two anime adaptations. Multiple Shin Megami Tensei and Persona titles have received manga and CD drama adaptations. Action figures and merchandise related to Persona have also been produced. == Common elements == Despite most games in the series taking place in different continuities, they do share certain elements
Oblivion (2013 film)
Oblivion is a 2013 American epic post-apocalyptic science fiction action film produced and directed by Joseph Kosinski from a screenplay by Karl Gajdusek and Michael deBruyn, starring Tom Cruise in the main role alongside Morgan Freeman, Olga Kurylenko, Andrea Riseborough, Nikolaj Coster-Waldau, and Melissa Leo in supporting roles. Based on Kosinski's unpublished Radical Comics graphic novel of the same name, the film pays homage to 1970s sci-fi, and is a "love story" set in 2077 on an Earth desolated by an alien war; a maintenance technician on the verge of completing his mission finds a woman who survived from a space ship crash, leading him to question his purpose and discover the truth about the war. Oblivion premiered in Buenos Aires on March 26, 2013, and was released in theaters by Universal Pictures on April 19. The film grossed $286 million worldwide on a production budget of $120 million and received mixed reviews from critics. == Plot == In 2017, aliens known as Scavengers attack Earth and destroy the Moon, triggering global natural disasters. Although humanity wins the war using nuclear weapons, Earth is left uninhabitable. Sixty years later, the remnants of humanity have relocated to a colony on Saturn's moon Titan, except for Unit 49—technician Jack and his communications officer Victoria—who are scheduled to join them in two weeks. The pair oversee hydro rigs that convert seawater into fusion energy for the Tet, the last remaining human colony ship in orbit. Though Jack and Victoria are romantically involved and have had their memories erased for security reasons, Jack experiences recurring dreams of an unknown woman. He also secretly visits a hidden, verdant valley where he has built a lakeside cabin and collects relics of Earth's past. While investigating a missing drone—autonomous, highly advanced, and heavily armed machines—Jack is nearly captured by Scavengers. Later, he discovers the Scavengers are transmitting a signal into space. A NASA pod crash-lands at the signal's coordinates, carrying five humans in suspended animation, including the woman from Jack's dreams. A drone arrives and destroys four of the pods, but Jack rescues the remaining one and brings the unconscious woman to Unit 49's base. After reviving her, Jack and Victoria learn that the woman, Julia, has been in stasis aboard the Odyssey spaceship since 2017. Julia insists on recovering the ship's flight recorder. However, she and Jack are captured by Scavengers and brought to the Raven Rock Mountain Complex. Their leader, Malcolm, reveals that the Scavengers are actually surviving humans. Malcolm needs Jack to reprogram a captured drone to deliver a nuclear bomb, built from Odyssey's reactor, to the Tet. Jack refuses, so Malcolm releases him and Julia, urging him to seek the truth in the radiation zone, which is supposedly deadly and off-limits. Julia helps Jack recall that she is his wife, and fragments of his memories begin to return. When they arrive back at Unit 49, a devastated Victoria informs Sally, the Tet's mission controller, that she and Jack are no longer an "effective team." A drone activates and kills Victoria. Jack and Julia destroy the drone, but crash their aircraft inside the radiation zone. There, they encounter another version of Jack—"Jack-52"—who arrives to repair the drone. Jack subdues him, but Julia is seriously injured in the fight. Jack impersonates his clone to infiltrate Unit 52, meets Victoria-52, and steals medical supplies for Julia. They rest at his cabin. At Raven Rock, Malcolm reveals the truth: humanity lost the war, and the Tet is an alien machine intelligence harvesting Earth's resources. After the Moon's destruction, the Tet deployed thousands of clones of astronaut Jack Harper—brainwashed into obedience—to exterminate the remaining humans. Malcolm had assumed these clones were inhuman until witnessing Jack show interest in a discarded book, hinting at lingering humanity. Jack reprograms the captured drone, but it is destroyed in a surprise attack by other drones, leaving Malcolm badly wounded. Jack and Julia resolve to deliver the bomb themselves; Julia enters a stasis pod. En route, Jack listens to the Odyssey's flight recorder, which reveals the original Jack Harper and Victoria were astronauts sent to explore Titan before being confronted by the Tet. The pair were captured, but not before Jack ejected the remaining crew—including Julia—in stasis pods to protect them. Jack gains access to the Tet by claiming he is delivering Julia, as previously instructed. However, the stasis pod contains a dying Malcolm. Jack and Malcolm detonate the bomb, destroying the Tet and themselves. Julia later awakens at the cabin. Three years later, Julia lives there and it is revealed she had a daughter with Jack. A group of Raven Rock survivors arrives, alongside Jack-52, who has begun regaining fragments of his own lost identity. == Cast == Tom Cruise as Jack Harper—Tech 49, a technician who works to repair drones on Earth and questions his mission. Originally, he was the American commander of a mission en route to Titan who was captured by the Tet and cloned to fight humanity. Cruise also plays Jack Harper—Tech 52, a clone who seeks out Julia after the destruction of the Tet. Morgan Freeman as Malcolm Beech, an American veteran soldier and leader of a large community of scavengers, the human survivors of the alien Tet's attacks. Olga Kurylenko as Julia Rusakova Harper, Jack's wife and a Russian crew member on the Odyssey, who was sent back towards Earth by her husband to protect her from the initial contact with the Tet. Andrea Riseborough as Victoria "Vika" Olsen, Jack's communications partner and housemate. Originally, she was the British co-pilot of Jack's mission to Titan who was captured and cloned to assist in the Tet's war on humanity. Riseborough also plays a clone of Vika who Jack misleads to obtain medical supplies. Nikolaj Coster-Waldau as Sergeant Sykes, the main military commander of Beech's community of scavengers who is skeptical of Jack at first. Melissa Leo as the Tet, an alien artificial intelligence seeking to acquire Earth's natural resources and wipe out humanity. Leo also plays Sally, the mission director of Jack and Julia's mission to Titan; her likeness was copied by the Tet to serve as its visual and auditory representation. Zoë Bell as Kara, a soldier and member of the scavengers. == Production == === Development === Joseph Kosinski started the movie process by beginning work on a graphic novel called Oblivion featuring his story. While the completion of this would be teased to the public and the concept was used to pitch the movie, it was never finished and Kosinski claims he never intended to, stating it was "just a stage in the project [of film development]". Arvid Nelson was billed as co-writer and Radical Comics was attached as publisher. The novel was never finished; Kosinski explaining: "the partnership with Radical Comics allowed me to continue working on the story by developing a series of images and continuing to refine the story more over a period of years. Then I basically used all that development as a pitch kit to the studio. So even though we really never released it as an illustrated novel the story is being told as a film, which was always the intention." Walt Disney Pictures, which produced Kosinski's previous film Tron: Legacy (2010), acquired the Oblivion film adaptation rights from Radical Comics and Kosinski after a heated auction in August 2010. The film was a directing vehicle for Kosinski, with Barry Levine producing, and Jesse Berger executive producing. Other studios that made bids on the film were Paramount Pictures, 20th Century Fox, and Universal Pictures. Disney subsequently released the rights after realizing the PG-rated film they envisioned, in line with their family-oriented reputation, would require too many story changes. Universal, which had also bid for the original rights, then bought them from Kosinski and Radical and authorized a PG-13 film version. The film's script was originally written by Kosinski and William Monahan and underwent a first rewrite by Karl Gajdusek. When the film passed into Universal's hands, a final rewrite was done by Michael Arndt, under the pen name "Michael deBruyn". Universal was particularly appreciative of the script, saying, "It's one of the most beautiful scripts we've ever come across." The Bubble Ship operated by Cruise's main character, Jack 49, was inspired by the Bell 47 helicopter (often colloquially referred to as a "bubble cockpit" helicopter), a utilitarian 1947 vehicle with a transparent round canopy that Kosinski saw in the lobby of the Museum of Modern Art in Manhattan, and which he likened to a dragonfly. Daniel Simon, who previously worked with Kosinski as the lead vehicle designer on Tron: Legacy, was tasked with creating the Bubble Ship from this basis, incorporating elements evocative of an advanced fighter
AAAI Conference on Artificial Intelligence
The AAAI Conference on Artificial Intelligence is a leading international academic conference in artificial intelligence held annually. It ranks 4th in terms of H5 Index in Google Scholar's list of top AI publications, after ICLR, NeurIPS, and ICML. It is supported by the Association for the Advancement of Artificial Intelligence (AAAI), after which it is named. Precise dates vary from year to year, but paper submissions are generally due at the end of August to beginning of September, and the conference is generally held during the following February. The first AAAI was held in 1980 at Stanford University, Stanford California. During AAAI-20 conference, AI pioneers and 2018 Turing Award winners (often referred to as the Nobel Prize of Computing) Yann LeCun and Yoshua Bengio, among eight other researchers, were honored as the AAAI 2020 Fellows. Along with other conferences such as NeurIPS and ICML, AAAI uses an artificial-intelligence algorithm to assign papers to reviewers. == Sponsors == Many leading technology companies, including Google, Microsoft, Amazon (company), IBM, Baidu, Bytedance, and Huawei, generously sponsor and participate in AAAI to publish and showcase their latest theoretical and applied research. Sponsoring companies also actively recruit AI talents at the conference. == Locations == AAAI-2026 Singapore Expo, Singapore AAAI-2025 Pennsylvania Convention Center, Philadelphia, Pennsylvania, United States AAAI-2024 Vancouver Convention Centre, Vancouver, British Columbia, Canada AAAI-2023 Washington Convention Center, Washington, D.C., United States AAAI-2022 Virtual Conference AAAI-2021 Virtual Conference AAAI-2020 Hilton New York Midtown, New York, New York, United States AAAI-2019 Hilton Hawaiian Village, Honolulu, Hawaii, United States AAAI-2018 Hilton New Orleans Riverside, New Orleans, Louisiana, United States AAAI-2017 San Francisco, California, United States AAAI-2016 Phoenix, Arizona, United States AAAI-2015 Austin, Texas, United States AAAI-2014 Québec Convention Center, Québec City, Québec, Canada AAAI-2013 Bellevue, Washington, United States AAAI-2012 Toronto, Ontario, Canada AAAI-2011 San Francisco, California, United States AAAI-2010 Westin Peachtree Plaza, Atlanta, Georgia, United States AAAI-2008 Chicago, Illinois, United States AAAI-2007 Toronto, Ontario, Canada AAAI-2006 Boston, Massachusetts, United States AAAI-2005 Pittsburgh, Pennsylvania, United States AAAI-2004 San Jose, California, United States AAAI-2002 Shaw conference center in Edmonton, Alberta, Canada AAAI-2000 Austin, Texas, United States AAAI-1999 Orlando, Florida, United States AAAI-1998 Madison, Wisconsin, United States AAAI-1997 Providence, Rhode Island, United States AAAI-1996 Portland, Oregon, United States AAAI-1994 Seattle, Washington, United States AAAI-1993 Washington Convention Center, Washington, D.C., United States AAAI-1992 San Jose Convention Center, San Jose, California, United States AAAI-1991 Anaheim Convention Center, Anaheim, California, United States AAAI-1990 Boston, Massachusetts, United States AAAI-1988 Saint Paul, Minnesota, United States AAAI-1987 Seattle, Washington, United States AAAI-1986 Philadelphia, Pennsylvania, United States AAAI-1984 University of Texas, Austin, Texas, United States AAAI-1983 Washington, D.C., United States AAAI-1982 Carnegie Mellon University and the University of Pittsburgh, Pittsburgh, Pennsylvania, United States AAAI-1980 Stanford, California, United States
Speech recognition
Speech recognition (automatic speech recognition (ASR), computer speech recognition, or speech-to-text (STT)) is a sub-field of computational linguistics concerned with methods and technologies that translate spoken language into text or other interpretable forms. Speech recognition applications include voice user interfaces, where the user speaks to a device, which "listens" and processes the audio. Common voice applications include interpreting commands for calling, call routing, home automation, and aircraft control. These applications are called direct voice input. Productivity applications include searching audio recordings, creating transcripts, and dictation. Speech recognition can be used to analyse speaker characteristics, such as identifying native language using pronunciation assessment. Voice recognition (speaker identification) refers to identifying the speaker, rather than speech contents. Recognizing the speaker can simplify the task of translating speech in systems trained on a specific person's voice. It can also be used to authenticate the speaker as part of a security process. == History == Applications for speech recognition developed over many decades, with progress accelerated due to advances in deep learning and the use of big data. These advances are reflected in an increase in academic papers, and greater system adoption. Key areas of growth include vocabulary size, more accurate recognition for unfamiliar speakers (speaker independence), and faster processing speed. === Pre-1970 === 1952 – Bell Labs researchers, Stephen Balashek, R. Biddulph, and K. H. Davis, built Audrey for single-speaker digit recognition. Their system located the formants in the power spectrum of each utterance. 1960 – Gunnar Fant developed and published the source–filter model of speech production. 1962 – IBM's 16-word "Shoebox" machine's speech recognition debuted at the 1962 World's Fair. 1966 – Linear predictive coding, a speech coding method, was proposed by Fumitada Itakura of Nagoya University and Shuzo Saito of Nippon Telegraph and Telephone. 1969 – Funding at Bell Labs came to a halt for several years after the company's head engineer, John R. Pierce, wrote an open letter criticizing speech recognition research. This defunding lasted until Pierce retired and James L. Flanagan took over. Raj Reddy was the first person to work on continuous speech recognition, as a graduate student at Stanford University in the late 1960s. Previous systems required users to pause after each word. Reddy's system issued spoken commands for playing chess. Around this time, Soviet researchers invented the dynamic time warping (DTW) algorithm and used it to create a recognizer capable of operating on a 200-word vocabulary. DTW processed speech by dividing it into short frames (e.g. 10 ms segments) and treating each frame as a unit. Speaker independence, however, remained unsolved. === 1970–1990 === 1971 – DARPA funded a five-year speech recognition research project, Speech Understanding Research, seeking a minimum vocabulary size of 1,000 words. The project considered speech understanding a key to achieving progress in speech recognition, which was later disproved. BBN, IBM, Carnegie Mellon (CMU), and Stanford Research Institute participated. 1972 – The IEEE Acoustics, Speech, and Signal Processing group held a conference in Newton, Massachusetts. 1976 – The first ICASSP was held in Philadelphia, which became a major venue for publishing on speech recognition. During the late 1960s, Leonard Baum developed the mathematics of Markov chains at the Institute for Defense Analysis. A decade later, at CMU, Raj Reddy's students James Baker and Janet M. Baker began using the hidden Markov model (HMM) for speech recognition. James Baker had learned about HMMs while at the Institute for Defense Analysis. HMMs enabled researchers to combine sources of knowledge, such as acoustics, language, and syntax, in a unified probabilistic model. By the mid-1980s, Fred Jelinek's team at IBM created a voice-activated typewriter called Tangora, which could handle a 20,000-word vocabulary. Jelinek's statistical approach placed less emphasis on emulating human brain processes in favor of statistical modelling. (Jelinek's group independently discovered the application of HMMs to speech.) This was controversial among linguists since HMMs are too simplistic to account for many features of human languages. However, the HMM proved to be a highly useful way for modelling speech and replaced dynamic time warping as the dominant speech recognition algorithm in the 1980s. 1982 – Dragon Systems, founded by James and Janet M. Baker, was one of IBM's few competitors. === Practical speech recognition === The 1980s also saw the introduction of the n-gram language model. 1987 – The back-off model enabled language models to use multiple-length n-grams, and CSELT used HMM to recognize languages (in software and hardware, e.g. RIPAC). At the end of the DARPA program in 1976, the best computer available to researchers was the PDP-10 with 4 MB of RAM. It could take up to 100 minutes to decode 30 seconds of speech. Practical products included: 1984 – the Apricot Portable was released with up to 4096 words support, of which only 64 could be held in RAM at a time. 1987 – a recognizer from Kurzweil Applied Intelligence 1990 – Dragon Dictate, a consumer product released in 1990. AT&T deployed the Voice Recognition Call Processing service in 1992 to route telephone calls without a human operator. The technology was developed by Lawrence Rabiner and others at Bell Labs. By the early 1990s, the vocabulary of the typical commercial speech recognition system had exceeded the average human vocabulary. Reddy's former student, Xuedong Huang, developed the Sphinx-II system at CMU. Sphinx-II was the first to do speaker-independent, large vocabulary, continuous speech recognition, and it won DARPA's 1992 evaluation. Handling continuous speech with a large vocabulary was a major milestone. Huang later founded the speech recognition group at Microsoft in 1993. Reddy's student Kai-Fu Lee joined Apple, where, in 1992, he helped develop the Casper speech interface prototype. Lernout & Hauspie, a Belgium-based speech recognition company, acquired other companies, including Kurzweil Applied Intelligence in 1997 and Dragon Systems in 2000. L&H was used in Windows XP. L&H was an industry leader until an accounting scandal destroyed it in 2001. L&H speech technology was bought by ScanSoft, which became Nuance in 2005. Apple licensed Nuance software for its digital assistant Siri. ==== 2000s ==== In the 2000s, DARPA sponsored two speech recognition programs: Effective Affordable Reusable Speech-to-Text (EARS) in 2002, followed by Global Autonomous Language Exploitation (GALE) in 2005. Four teams participated in EARS: IBM; a team led by BBN with LIMSI and the University of Pittsburgh; Cambridge University; and a team composed of ICSI, SRI, and the University of Washington. EARS funded the collection of the Switchboard telephone speech corpus, which contained 260 hours of recorded conversations from over 500 speakers. The GALE program focused on Arabic and Mandarin broadcast news. Google's first effort at speech recognition came in 2007 after recruiting Nuance researchers. Its first product, GOOG-411, was a telephone-based directory service. Since at least 2006, the U.S. National Security Agency has employed keyword spotting, allowing analysts to index large volumes of recorded conversations and identify speech containing "interesting" keywords. Other government research programs focused on intelligence applications, such as DARPA's EARS program and IARPA's Babel program. In the early 2000s, speech recognition was dominated by hidden Markov models combined with feed-forward artificial neural networks (ANN). Later, speech recognition was taken over by long short-term memory (LSTM), a recurrent neural network (RNN) published by Sepp Hochreiter & Jürgen Schmidhuber in 1997. LSTM RNNs avoid the vanishing gradient problem and can learn "Very Deep Learning" tasks that require memories of events that happened thousands of discrete time steps earlier, which is important for speech. Around 2007, LSTMs trained with Connectionist Temporal Classification (CTC) began to outperform. In 2015, Google reported a 49 percent error‑rate reduction in its speech recognition via CTC‑trained LSTM. Transformers, a type of neural network based solely on attention, were adopted in computer vision and language modelling, and then to speech recognition. Deep feed-forward (non-recurrent) networks for acoustic modelling were introduced in 2009 by Geoffrey Hinton and his students at the University of Toronto, and by Li Deng and colleagues at Microsoft Research. In contrast to the prioer incremental improvements, deep learning decreased error rates by 30%. Both shallow and deep forms (e.g., recurrent nets) of ANNs had been explored since the 1980s. Howev
HYPO CBR
HYPO is a computer program, an expert system, that models reasoning with cases and hypotheticals in the legal domain. It is the first of its kind and the most sophisticated of the case-based legal reasoners, which was designed by Kevin Ashley for his Ph.D dissertation in 1987 at the University of Massachusetts Amherst under the supervision of Edwina Rissland. HYPO's design represents a hybrid generalization/comparative evaluation method appropriate for a domain with a weak analytical theory and applies to tasks that rarely involve just one right answer. The domain covers US trade secret law, and is substantially a common law domain. Since Anglo-American common law operates under the doctrine of precedent, the definitive way of interpreting problems is of necessity and case-based. Thus, HYPO did not involve the analysis of a statute, as required by the Prolog program. Rissland and Ashley (1987) envisioned HYPO as employing the key tasks performed by lawyers when analyzing case law for precedence to generate arguments for the prosecution or the defence. HYPO was a successful example of a general category of legal expert systems (LESs), it applies artificial intelligence (A.I.) techniques to the domain of legal reasoning in patent law, implementing a case-based reasoning (CBR) system, in contrast to rule based systems like MYCIN, or mixed-paradigm systems integrating CBR with rule-based or model-based reasoning like IKBALS II. A legal case-based reasoning essentially reasons from prior tried cases, comparing the contextual information in the current input case with that of cases previously tried and entered into the system. As noted by Ashley and Rissland (1988) CBR is used to "... capture expertise in domains where rules are ill-defined, incomplete or inconsistent". The HYPO project set out to model the creation of hypotheticals in law, where no case matches well enough. HYPO uses hypotheticals for a variety of tasks necessary for good interpretation: "to redefine old situations in terms of new dimensions, to create new standard cases when an appropriate one doesn’t exist, to explore and test the limits of a concept, to refocus a case by excluding some issues and to organize or cluster cases". Hypotheticals can include facts that support two conflicting lines of reasoning. So, it makes and responds to arguments from competing viewpoints about who should win the dispute. HYPO use heuristics such as making a case weaker or stronger, making a case extreme, enabling a near-miss, disabling a near-hit to generate hypotheticals in the context of an argument by using the dimensions mechanism. Dimensions have a range of values, along which the supportive strength that may shift from one side to the other. What differentiated this expert system from others was its facility not only to return a primary to best-case response but to return near-best-fit responses also. == Components == Legal knowledge in HYPO is contained in: the case-knowledge-base (CKB) and the library of dimensions. The CKB contains HYPO's base of known cases that are highly structured objects and sub-objects both real and hypothetical in the area of trade secret law. Each case is represented as a hierarchical set of frames whose slots are important facets of the case (e.g. Plaintiff, defendant, secret knowledge, employer/employee data).Ashley’s HYPO system used a database of thirty cases in the area indexed by thirteen dimensions. A key mechanism in HYPO is a dimension i.e. a mechanism to allow retrieval from the CKB, in order to represent legal cases. Ashley's dimensions are composed of (i) prerequisites, which are a set of factual predicates that must be satisfied for the dimension to apply (ii) focal slots, which accommodate one or two of the dimension's prerequisites designated as being indicative of the case's strength along that dimension and (iii) range information, which tells how a change in focal slot value effects the strength of a party's case along a given dimension. Dimensions focus attention on important aspects of cases. In HYPO's domain of misappropriation of trade secrets the dimension called “secrets voluntary disclosed” captures the idea that the more disclosures the plaintiff has made of his/her putative secret, the less convincing is his/her argument that the defendant is responsible for letting the secret. HYPO, like any other CBR system has also the following components: Similarity/relevancy metrics: that is, standards by which to evaluate the closeness of cases, judge their relevancy to the instant case, and select “most on point” cases. Half-Order Theory of the Application Domain: that is, hierarchies and taxonomies of knowledge, especially regarding the application domain. Precedent-based argumentation abilities: that is, capabilities to generate and evaluate precedent-based arguments. Knowledge to generate hypotheticals: that is, the ability to generate hypothetical cases to deal with various circumstances, like testing the validity of an interpretation or argument by providing gedanken experiments such as test cases or to fill in a weak CKB. == Functions == HYPO's method of creating an argument and justifying a solution or position has several steps. HYPO begins its processing with the current fact situation (cfs) which is direct input by the user into HYPO's representation framework. Once the user inputs the case, HYPO begins its legal analysis. The cfc is analyzed for relevant factors. Based on these factors HYPO selects the relevant cases and produces a case-analysis-record that records which dimensions apply to the cfc and which nearly apply (i.e. are "near misses"). The combined list of applicable and near miss dimensions is called the D-list. At this point the fact gathered module may request additional information from the user in order to draw a legal conclusion. Once all the facts are in the case-positioner module it uses the case-analysis record to create the claim lattice. This is a technique that organizes the relevant retrieved cases from the point of view of the cfc and makes it easy for HYPO to ascertain the most-on point cases (mopc) and to least on-point-cases. HYPO's arguments are 3ply, leading to the construction of the skeleton of an argument: it makes a point for one side, drawing the analogy between the problem and the precedent, responds with an argument for the opponent side, endeavoring to differentiate the cited case and citing other cases as counterarguments. Then it makes a final rebuttal, attempting to differentiate the counterarguments. The claim lattice also enables the HYPO-generator module to produce legally hypotheticals. With its use of dimension-based heuristics, the HYPO-generator does a heuristic search of the space of all possible cases. Lastly, the Explanation module expands upon the argument skeleton and provides explanation and justification for the different lines of analysis and cases found by HYPO. == An intelligent legal tutoring system == Legal expert systems are specifically designed to teach an area of law and are useful for pedagogical purposes. Ashley's work was mainly concerned to build tools to help students understand legal reasoning. Explanation and argument are the bases of the case method used in many professional schools in the U.S., first introduced by the Dean of the Harvard Law School, Christopher Columbus Langdell in 1870. The case method focuses on close readings of cases and principles; it involves students in pointed Socratic dialogue and makes strong use of hypotheticals (hypos). Thus, CATO (Aleven 1997) was a research project to device and test an intelligent, case-based tutorial program for teaching law students how to argue with cases implementing the HYPO program. Within the tutor system, Ashley and Aleven (1991) proposed to leverage an understanding of legal reasoning against the standard case-based tutoring methodology. What makes this tutoring system stand out is the additional levels of abstraction involved in its results. The system presents exercises, including the facts of a problem and a set of on-line cases and instructions to make, or respond to, a legal argument about the problem. The student/user will have a set of tools to analyze the problem and fashion an answer comparing it to other cases. Instead of simply generating precedent cases, the system works to interpret student responses, comparing them against a list of possibilities and responding to student entries, for example, by citing counterexamples, and providing feedback on a student's problem solving activities with explanations of correctness or giving further hints as to what may be wrong with evaluating a student's ability to perform legal reasoning and argument, examples and follow-up assignments by employing HYPO's model of case-based structure. == HYPO’s progeny == The quality of HYPO's results speak for themselves, in that a number of sequent legal reasoning systems are either directly based upon H