Ernst Dieter Dickmanns is a German pioneer of dynamic computer vision and of driverless cars. Dickmanns has been a professor at the University of the Bundeswehr Munich (1975–2001), and visiting professor to Caltech and to MIT, teaching courses on "dynamic vision". == Biography == Dickmanns was born in 1936. He studied aerospace and aeronautics at RWTH Aachen (1956–1961), and control engineering at Princeton University (1964/65); from 1961 to 1975 he was associated with the German Aero-Space Research Establishment (now DLR) Oberpfaffenhofen, working in the fields of flight dynamics and trajectory optimization. In 1971/72 he spent a Post-Doc Research Associateship with the NASA-Marshall Space Flight Center, Huntsville (orbiter re-entry). From 1975 to 2001 he was with UniBw Munich, where he initiated the 'Institut fuer Flugmechanik und Systemdynamik' (IFS), the Institut fuer die 'Technik Autonomer Systeme' (TAS), and the research activities in machine vision for vehicle guidance. == Pioneering work in autonomous driving == In the early 1980s his team equipped a Mercedes-Benz van with cameras and other sensors. The 5-ton van was re-engineered that it was possible to control steering wheel, throttle, and brakes through computer commands based on real-time evaluation of image sequences. Software was written that translated the sensory data into appropriate driving commands. For safety reasons, initial experiments in Bavaria took place on streets without traffic. In 1986 the Robot Car "VaMoRs" managed to drive all by itself and by 1987 was capable of driving itself at speeds up to 96 kilometres per hour (60 mph). One of the greatest challenges in high-speed autonomous driving arises through the rapidly changing visual street scenes. Back then, computers were much slower than they are today (~1% of 1%); therefore, sophisticated computer vision strategies were necessary to react in real time. The team of Dickmanns solved the problem through an innovative approach to dynamic vision. Spatiotemporal models were used right from the beginning, dubbed '4-D approach', which did not need storing previous images but nonetheless was able to yield estimates of all 3-D position and velocity components. Attention control including artificial saccadic movements of the platform carrying the cameras allowed the system to focus its attention on the most relevant details of the visual input. Kalman filters have been extended to perspective imaging and were used to achieve robust autonomous driving even in presence of noise and uncertainty. Feedback of prediction errors allowed bypassing the (ill-conditioned) inversion of perspective projection by least-squares parameter fits. When in 1986/83 the EUREKA-project 'PROgraMme for a European Traffic of Highest Efficiency and Unprecedented Safety' (PROMETHEUS) was initiated by the European car manufacturing industry (funding in the range of several hundred million Euros), the initially planned autonomous lateral guidance by buried cables was dropped and substituted by the much more flexible machine vision approach proposed by Dickmanns, and partially encouraged by his successes. Most of the major car companies participated; so did Dickmanns and his team in cooperation with the Daimler-Benz AG. Substantial progress was made in the following 7 years. In particular, Dickmanns' robot cars learned to drive in traffic under various conditions. An accompanying human driver with a "red button" made sure the robot vehicle could not get out of control and become a danger to the public. Since 1992, driving in public traffic was standard as final step in real-world testing. Several dozen Transputers, a special breed of parallel computers, were used to deal with the (by 1990s standards) enormous computational demands. Two culmination points were achieved in 1994/95, when Dickmanns´ re-engineered autonomous S-Class Mercedes-Benz performed international demonstrations. The first was the final presentation of the PROMETHEUS project in October 1994 on Autoroute 1 near the airport Charles-de-Gaulle in Paris. With guests on board, the twin vehicles of Daimler-Benz (VITA-2) and UniBwM (VaMP) drove more than 1,000 kilometres (620 mi) on the three-lane highway in standard heavy traffic at speeds up to 130 kilometres per hour (81 mph). Driving in free lanes, convoy driving with distance keeping depending on speed, and lane changes left and right with autonomous passing have been demonstrated; the latter required interpreting the road scene also in the rear hemisphere. Two cameras with different focal lengths for each hemisphere have been used in parallel for this purpose. The second culmination point was a 1,758 kilometres (1,092 mi) trip in the fall of 1995 from Munich in Bavaria to Odense in Denmark to a project meeting and back. Both longitudinal and lateral guidance were performed autonomously by vision. On highways, the robot achieved speeds exceeding 175 kilometres per hour (109 mph) (there is no general speed limit on the Autobahn). Publications from Dickmann's research group indicate a mean autonomously driven distance without resets of ~9 kilometres (5.6 mi); the longest autonomously driven stretch reached 158 kilometres (98 mi). More than half of the resets required were achieved autonomously (no human intervention). This is particularly impressive considering that the system used black-and-white video-cameras and did not model situations like road construction sites with yellow lane markings; lane-changes at over 140 kilometres per hour (87 mph), and other traffic with more than 40 kilometres per hour (25 mph) relative speed have been handled. In total, 95% autonomous driving (by distance) was achieved. In the years 1994 to 2004 the elder 5-ton van 'VaMoRs' was used to develop the capabilities needed for driving on networks of minor (also unsealed) roads and for cross-country driving including avoidance of negative obstacles like ditches. Turning off onto crossroads of unknown width and intersection angles required a big effort, but has been achieved with "Expectation-based, Multi-focal, Saccadic vision" (EMS-vision). This vertebrate-type vision uses animation capabilities based on knowledge about subject classes (including the autonomous vehicle itself) and their potential behaviour in certain situations. This rich background is used for control of gaze and attention as well as for locomotion. Beside ground vehicle guidance, also applications of the 4-D approach to dynamic vision for unmanned air vehicles (conventional aircraft and helicopters) have been investigated. Autonomous visual landing approaches and landings have been demonstrated in hardware-in-the-loop simulations with visual/inertial data fusion. Real-world autonomous visual landing approaches till shortly before touchdown have been performed in 1992 with the twin-propeller aircraft Dornier 128 of the University of Brunswick at the airport there. Another success of this machine vision technology was the first ever visually controlled grasping experiment of a free-floating object in weightlessness on board the Space Shuttle Columbia D2-mission in 1993 as part of the 'Rotex'-experiment of DLR.
Information extraction
Information extraction (IE) is the task of automatically extracting structured information from unstructured and/or semi-structured machine-readable documents and other electronically represented sources. Typically, this involves processing human language texts by means of natural language processing (NLP). Recent activities in multimedia document processing like automatic annotation and content extraction out of images/audio/video/documents could be seen as information extraction. Recent advances in NLP techniques have allowed for significantly improved performance compared to previous years. An example is the extraction from newswire reports of corporate mergers, such as denoted by the formal relation: MergerBetween ( c o m p a n y 1 , c o m p a n y 2 , d a t e ) {\displaystyle \operatorname {MergerBetween} (\mathrm {company} _{1},\mathrm {company} _{2},\mathrm {date} )} , from an online news sentence such as: "Yesterday, New York based Foo Inc. announced their acquisition of Bar Corp." A broad goal of IE is to allow computation to be done on the previously unstructured data. A more specific goal is to allow automated reasoning about the logical form of the input data. Structured data is semantically well-defined data from a chosen target domain, interpreted with respect to category and context. Information extraction is the part of a greater puzzle which deals with the problem of devising automatic methods for text management, beyond its transmission, storage and display. The discipline of information retrieval (IR) has developed automatic methods, typically of a statistical flavor, for indexing large document collections and classifying documents. Another complementary approach is that of natural language processing (NLP) which has solved the problem of modelling human language processing with considerable success when taking into account the magnitude of the task. In terms of both difficulty and emphasis, IE deals with tasks in between both IR and NLP. In terms of input, IE assumes the existence of a set of documents in which each document follows a template, i.e. describes one or more entities or events in a manner that is similar to those in other documents but differing in the details. An example, consider a group of newswire articles on Latin American terrorism with each article presumed to be based upon one or more terroristic acts. We also define for any given IE task a template, which is a(or a set of) case frame(s) to hold the information contained in a single document. For the terrorism example, a template would have slots corresponding to the perpetrator, victim, and weapon of the terroristic act, and the date on which the event happened. An IE system for this problem is required to "understand" an attack article only enough to find data corresponding to the slots in this template. == History == Information extraction dates back to the late 1970s in the early days of NLP. An early commercial system from the mid-1980s was JASPER built for Reuters by the Carnegie Group Inc with the aim of providing real-time financial news to financial traders. Beginning in 1987, IE was spurred by a series of Message Understanding Conferences. MUC is a competition-based conference that focused on the following domains: MUC-1 (1987), MUC-3 (1989): Naval operations messages. MUC-3 (1991), MUC-4 (1992): Terrorism in Latin American countries. MUC-5 (1993): Joint ventures and microelectronics domain. MUC-6 (1995): News articles on management changes. MUC-7 (1998): Satellite launch reports. Considerable support came from the U.S. Defense Advanced Research Projects Agency (DARPA), who wished to automate mundane tasks performed by government analysts, such as scanning newspapers for possible links to terrorism. == Present significance == The present significance of IE pertains to the growing amount of information available in unstructured form. Tim Berners-Lee, inventor of the World Wide Web, refers to the existing Internet as the web of documents and advocates that more of the content be made available as a web of data. Until this transpires, the web largely consists of unstructured documents lacking semantic metadata. Knowledge contained within these documents can be made more accessible for machine processing by means of transformation into relational form, or by marking-up with XML tags. An intelligent agent monitoring a news data feed requires IE to transform unstructured data into something that can be reasoned with. A typical application of IE is to scan a set of documents written in a natural language and populate a database with the information extracted. == Tasks and subtasks == Applying information extraction to text is linked to the problem of text simplification in order to create a structured view of the information present in free text. The overall goal being to create a more easily machine-readable text to process the sentences. Typical IE tasks and subtasks include: Template filling: Extracting a fixed set of fields from a document, e.g. extract perpetrators, victims, time, etc. from a newspaper article about a terrorist attack. Event extraction: Given an input document, output zero or more event templates. For instance, a newspaper article might describe multiple terrorist attacks. Knowledge Base Population: Fill a database of facts given a set of documents. Typically the database is in the form of triplets, (entity 1, relation, entity 2), e.g. (Barack Obama, Spouse, Michelle Obama) Named entity recognition: recognition of known entity names (for people and organizations), place names, temporal expressions, and certain types of numerical expressions, by employing existing knowledge of the domain or information extracted from other sentences. Typically the recognition task involves assigning a unique identifier to the extracted entity. A simpler task is named entity detection, which aims at detecting entities without having any existing knowledge about the entity instances. For example, in processing the sentence "M. Smith likes fishing", named entity detection would denote detecting that the phrase "M. Smith" does refer to a person, but without necessarily having (or using) any knowledge about a certain M. Smith who is (or, "might be") the specific person whom that sentence is talking about. Coreference resolution: detection of coreference and anaphoric links between text entities. In IE tasks, this is typically restricted to finding links between previously extracted named entities. For example, "International Business Machines" and "IBM" refer to the same real-world entity. If we take the two sentences "M. Smith likes fishing. But he doesn't like biking", it would be beneficial to detect that "he" is referring to the previously detected person "M. Smith". Relationship extraction: identification of relations between entities, such as: PERSON works for ORGANIZATION (extracted from the sentence "Bill works for IBM.") PERSON located in LOCATION (extracted from the sentence "Bill is in France.") Semi-structured information extraction which may refer to any IE that tries to restore some kind of information structure that has been lost through publication, such as: Table extraction: finding and extracting tables from documents. Table information extraction : extracting information in structured manner from the tables. This task is more complex than table extraction, as table extraction is only the first step, while understanding the roles of the cells, rows, columns, linking the information inside the table and understanding the information presented in the table are additional tasks necessary for table information extraction. Comments extraction : extracting comments from the actual content of articles in order to restore the link between authors of each of the sentences Language and vocabulary analysis Terminology extraction: finding the relevant terms for a given corpus Audio extraction Template-based music extraction: finding relevant characteristic in an audio signal taken from a given repertoire; for instance time indexes of occurrences of percussive sounds can be extracted in order to represent the essential rhythmic component of a music piece. Note that this list is not exhaustive and that the exact meaning of IE activities is not commonly accepted and that many approaches combine multiple sub-tasks of IE in order to achieve a wider goal. Machine learning, statistical analysis and/or natural language processing are often used in IE. IE on non-text documents is becoming an increasingly interesting topic in research, and information extracted from multimedia documents can now be expressed in a high level structure as it is done on text. This naturally leads to the fusion of extracted information from multiple kinds of documents and sources. == World Wide Web applications == IE has been the focus of the MUC conferences. The proliferation of the Web, however, intensified the need for developing IE systems that help people
Age Of
Age Of is the eighth studio album by American electronic producer Oneohtrix Point Never, released on June 1, 2018, on Warp Records. Recorded over two years, it is the first Oneohtrix Point Never album to prominently feature Daniel Lopatin's own vocals. The album was accompanied by the MYRIAD tour, which premiered as a "conceptual concertscape" in 2018 at the Park Avenue Armory and ended its run in 2019. It features contributions from James Blake (who additionally produced and mixed the album), Anohni, Prurient, Kelsey Lu and Eli Keszler. The artwork, which employs Jim Shaw's "The Great Whatsit" as a central image, was designed by David Rudnick. While not entering the official United States Billboard 200 chart, it peaked at number 59 on the magazine's Top Current Albums chart. == Background == Lopatin produced Age Of in parts of a two-year period, during which he was also producing for other artists, including Anohni, FKA Twigs, Iggy Pop, and David Byrne. After composing the soundtrack for the Safdie Brothers' 2017 film Good Time, Lopatin moved to an Airbnb lodge in South Central Massachusetts, derived from his aspiration to live out the modern cliche of musicians moving to the woods to record albums; the eerie atmosphere in the lodge at nighttime influenced his desire to make "weird, little nightmare ballads". In addition to Lopatin's own singing, the album also features vocal performances from Anohni and Prurient, while instrumentalists Kelsey Lu and Eli Keszler contribute to several tracks. When the record was nearly finished, Lopatin reached out to musician James Blake to contribute to the mixing process, eventually traveling to Los Angeles to complete the album. The track "The Station" was originally composed as a demo for R&B singer Usher which was ultimately not used. On July 9, 2018, Lopatin released the original topline (vocal melody) demo for The Station through Sendspace. The track "Toys 2" imagines a theoretical sequel to the 1992 film Toys where actor Robin Williams' image has been recreated with CGI (as his will specifically forbade any usage of his image after his death), and pokes fun at the common electronic music trope of composing a soundtrack to a theoretical film (which Lopatin described as "horribly cliché"). == Concept and MYRIAD == Influences on Age Of included Stanley Kubrick's 1968 film 2001: A Space Odyssey, which inspired the narrative of the album's accompanying performance installation and tour MYRIAD, as well as William Strauss's The Fourth Turning, a favorite book of former White House Chief Strategist Steve Bannon, which Lopatin described as "insidious, like the voice of a computer insisting on the truth about history without any sensitivity given to how complex and non-linear systems might be"; Lopatin was subsequently inspired to "[use] that sort of taxonomy as a kind of farce to then create these little frameworks for understanding". Other inspirations included the writings of the 1990s multidisciplinary collective Cybernetic Culture Research Unit and the works of singer-songwriters such as Bruce Cockburn, Bob Dylan, and Paul Simon. Around the time Lopatin began finalizing Age Of in his Airbnb lodge, he began working on the concept for MYRIAD, a conceptual concert performance which premiered at Park Avenue Armory. He described the concept as a four-part "epochal song cycle" showcasing the idiocy of previous generations of living organisms. The loose story concerns a group of artificial intelligences near the end of time named a "Limitless Living Informational Intelligence" (represented in the MYRIAD logo as nine squares) which, for leisurely purposes, attempt to replicate the cultures and behaviors of the previously existent human species. It does this by determining an "average" of human experiences through the species' "recorded output", and does so through imperfect, heuristic techniques. The show was consequently divided into four sections, each representing an epoch of the cycle concept loosely inspired by the Strauss–Howe generational theory: the Age of Ecco, the Age of Harvest, the Age of Excess, and the Age of Bondage. Ecco is "a phase of pre-evolutionary ignorance", Harvest is "living in agrarian harmony with the world", Excess is "the age of unchecked industrial ambition", and Bondage is "an era of engorgement, wherein "we keep making more and more shit until there's no space left." MYRIAD mainly featured "three-hundred pound sculptures that hang from the ceiling like kebabs that secrete ooze", and a full ensemble that toured to perform songs from Age Of, including Eli Keszler, Kelly Moran and Aaron David Ross. The sculptures, as well as the visuals displayed on five polygon panels, were created by frequent Oneohtrix Point Never collaborator Nate Boyce. Initially, Lopatin planned for each of the album's four epoches to be represented by fragrances, the more noisy epochs being pleasant to the nose to make a "weird dissonance". However, due to lack of time and resources, that part of the plan was scrapped. == Composition == Whereas previous Oneohtrix Point Never albums followed musical styles from only distinctive eras, Age Of is the first album by Lopatin to incorporate elements of unique genres from a variety of periods, hence the "incompleteness" of its title according to reviewer Heather Phares, and his first pop-song-oriented release since his work for Ford & Lopatin. The sound palettes it uses are those from a variety of styles such as chamber pop, "android"-like folk and country music, yacht rock, smooth jazz, R&B, Future-style soul, black metal, new age, and stadium pop, as well as post-industrial sounds on tracks like "Warning", "We'll Take It" and "Same", and, in particular, baroque music and medieval music on the opening title track, "Age Of". Critics also noted elements of Lopatin's past discography being present on Age Of. The instrumentation of Age Of is made up of MIDI harpsichords, guitars, pianos, brass and vocals, as well as Lopatin's trademark unorthodox sound design, samples and synth presets. The LP's use of the harpsichord shows its similarities "with Eastern instruments such as the koto and with rapid-fire electronic melodies", wrote Phares. == Critical reception == Age Of was critically well-received upon its distribution. Some reviewers praised the album's use of collaborators. Reviewing the album for AllMusic, Heather Phares called Age Of a "landmark work" for Lopatin. She praised it as his "widest-ranging" release, elaborating that he "matches the album's ambition with plenty of emotion" and "gives his music exciting new shapes." Ross Devlin of The Skinny, in a five-star review of the record, also highlighted the album's amount of ambition, particularly the "wealth of exquisitely baroque moments, exploring history as a pliable, multi-dimensional rift", that gave it "exceptional sonic depth". The Observer praised Age Of for continuing the "off-kilter composition and unexpected instrumentation" of Lopatin's previous releases, and critic Matt McDermott highlighted that the producer increased his musical range with the record: "It's a dizzying trip meant to shore up Lopatin's status as an avant-garde auteur while aiding his forays into mainstream pop culture." Age Of was ranked the 15th best release of the year in The Wire magazine's annual critics' poll. == Track listing == Notes "Myriad Industries" is stylized as "myriad.industries". Sample credits "Age Of" contains a sample of "Blow the Wind" by Jocelyn Pook. "Manifold" contains a sample from "Overture (Ararat the Border Crossing)" by Tayfun Erdem; and a sample from "Venice Beach in Winter" (listed in the liner notes as "a keyboard sample from Reharmonization") by Julian Bradley. "Myriad Industries" contains a sample of "EchoSpace" by Gil Trythall. == Accolades == == Personnel == Daniel Lopatin – production, lead vocals, album art, design James Blake – additional production, mixing, keyboards Gabriel Schuman, Joshua Smith and Evan Sutton – assistance Greg Calbi – mastering David Rudnick – album art, design Prurient – vocals Kelsey Lu – keyboards Anohni – vocals Eli Keszler – drums Shaun Trujillo – words == Charts ==
Fuzzy control system
A fuzzy control system is a control system based on fuzzy logic – a mathematical system that analyzes analog input values in terms of logical variables that take on continuous values between 0 and 1, in contrast to classical or digital logic, which operates on discrete values of either 1 or 0 (true or false, respectively). Fuzzy logic is widely used in machine control. The term "fuzzy" refers to the fact that the logic involved can deal with concepts that cannot be expressed as the "true" or "false" but rather as "partially true". Although alternative approaches such as genetic algorithms and neural networks can perform just as well as fuzzy logic in many cases, fuzzy logic has the advantage that the solution to the problem can be cast in terms that human operators can understand, such that that their experience can be used in the design of the controller. This makes it easier to mechanize tasks that are already successfully performed by humans. == History and applications == Fuzzy logic was proposed by Lotfi A. Zadeh of the University of California at Berkeley in a 1965 paper. He elaborated on his ideas in a 1973 paper that introduced the concept of "linguistic variables", which in this article equates to a variable defined as a fuzzy set. Other research followed, with the first industrial application, a cement kiln built in Denmark, coming on line in 1976. Fuzzy systems were initially implemented in Japan. Interest in fuzzy systems was sparked by Seiji Yasunobu and Soji Miyamoto of Hitachi, who in 1985 provided simulations that demonstrated the feasibility of fuzzy control systems for the Sendai Subway. Their ideas were adopted, and fuzzy systems were used to control accelerating, braking, and stopping when the Namboku Line opened in 1987. In 1987, Takeshi Yamakawa demonstrated the use of fuzzy control, through a set of simple dedicated fuzzy logic chips, in an "inverted pendulum" experiment. This is a classic control problem, in which a vehicle tries to keep a pole mounted on its top by a hinge upright by moving back and forth. Yamakawa subsequently made the demonstration more sophisticated by mounting a wine glass containing water and even a live mouse to the top of the pendulum: the system maintained stability in both cases. Yamakawa eventually went on to organize his own fuzzy-systems research lab to help exploit his patents in the field. Japanese engineers subsequently developed a wide range of fuzzy systems for both industrial and consumer applications. In 1988 Japan established the Laboratory for International Fuzzy Engineering (LIFE), a cooperative arrangement between 48 companies to pursue fuzzy research. The automotive company Volkswagen was the only foreign corporate member of LIFE, dispatching a researcher for a duration of three years. Japanese consumer goods often incorporate fuzzy systems. Matsushita vacuum cleaners use microcontrollers running fuzzy algorithms to interrogate dust sensors and adjust suction power accordingly. Hitachi washing machines use fuzzy controllers to load-weight, fabric-mix, and dirt sensors and automatically set the wash cycle for the best use of power, water, and detergent. Canon developed an autofocusing camera that uses a charge-coupled device (CCD) to measure the clarity of the image in six regions of its field of view and use the information provided to determine if the image is in focus. It also tracks the rate of change of lens movement during focusing, and controls its speed to prevent overshoot. The camera's fuzzy control system uses 12 inputs: 6 to obtain the current clarity data provided by the CCD and 6 to measure the rate of change of lens movement. The output is the position of the lens. The fuzzy control system uses 13 rules and requires 1.1 kilobytes of memory. An industrial air conditioner designed by Mitsubishi uses 25 heating rules and 25 cooling rules. A temperature sensor provides input, with control outputs fed to an inverter, a compressor valve, and a fan motor. Compared to the previous design, the fuzzy controller heats and cools five times faster, reduces power consumption by 24%, increases temperature stability by a factor of two, and uses fewer sensors. Other applications investigated or implemented include: character and handwriting recognition; optical fuzzy systems; robots, including one for making Japanese flower arrangements; voice-controlled robot helicopters (hovering is a "balancing act" rather similar to the inverted pendulum problem); rehabilitation robotics to provide patient-specific solutions (e.g. to control heart rate and blood pressure ); control of flow of powders in film manufacture; elevator systems; and so on. Work on fuzzy systems is also proceeding in North America and Europe, although on a less extensive scale than in Japan. The US Environmental Protection Agency has investigated fuzzy control for energy-efficient motors, and NASA has studied fuzzy control for automated space docking: simulations show that a fuzzy control system can greatly reduce fuel consumption. Firms such as Boeing, General Motors, Allen-Bradley, Chrysler, Eaton, and Whirlpool have worked on fuzzy logic for use in low-power refrigerators, improved automotive transmissions, and energy-efficient electric motors. In 1995 Maytag introduced an "intelligent" dishwasher based on a fuzzy controller and a "one-stop sensing module" that combines a thermistor, for temperature measurement; a conductivity sensor, to measure detergent level from the ions present in the wash; a turbidity sensor that measures scattered and transmitted light to measure the soiling of the wash; and a magnetostrictive sensor to read spin rate. The system determines the optimum wash cycle for any load to obtain the best results with the least amount of energy, detergent, and water. It even adjusts for dried-on foods by tracking the last time the door was opened, and estimates the number of dishes by the number of times the door was opened. Xiera Technologies Inc. has developed the first auto-tuner for the fuzzy logic controller's knowledge base known as edeX. This technology was tested by Mohawk College and was able to solve non-linear 2x2 and 3x3 multi-input multi-output problems. Research and development is also continuing on fuzzy applications in software, as opposed to firmware, design, including fuzzy expert systems and integration of fuzzy logic with neural-network and so-called adaptive "genetic" software systems, with the ultimate goal of building "self-learning" fuzzy-control systems. These systems can be employed to control complex, nonlinear dynamic plants, for example, human body. == Fuzzy sets == The input variables in a fuzzy control system are in general mapped by sets of membership functions similar to this, known as "fuzzy sets". The process of converting a crisp input value to a fuzzy value is called "fuzzification". The fuzzy logic based approach had been considered by designing two fuzzy systems, one for error heading angle and the other for velocity control. A control system may also have various types of switch, or "ON-OFF", inputs along with its analog inputs, and such switch inputs of course will always have a truth value equal to either 1 or 0, but the scheme can deal with them as simplified fuzzy functions that happen to be either one value or another. Given "mappings" of input variables into membership functions and truth values, the microcontroller then makes decisions for what action to take, based on a set of "rules", each of the form: IF brake temperature IS warm AND speed IS not very fast THEN brake pressure IS slightly decreased. In this example, the two input variables are "brake temperature" and "speed" that have values defined as fuzzy sets. The output variable, "brake pressure" is also defined by a fuzzy set that can have values like "static" or "slightly increased" or "slightly decreased" etc. === Fuzzy control in detail === Fuzzy controllers are very simple conceptually. They consist of an input stage, a processing stage, and an output stage. The input stage maps sensor or other inputs, such as switches, thumbwheels, and so on, to the appropriate membership functions and truth values. The processing stage invokes each appropriate rule and generates a result for each, then combines the results of the rules. Finally, the output stage converts the combined result back into a specific control output value. The most common shape of membership functions is triangular, although trapezoidal and bell curves are also used, but the shape is generally less important than the number of curves and their placement. From three to seven curves are generally appropriate to cover the required range of an input value, or the "universe of discourse" in fuzzy jargon. As discussed earlier, the processing stage is based on a collection of logic rules in the form of IF-THEN statements, where the IF part is called the "antecedent" and the THEN part is called the "consequent". Typical fuzzy
Mark I Perceptron
The Mark I Perceptron was a pioneering supervised image classification learning system developed by Frank Rosenblatt in 1958. It was the first implementation of an artificial intelligence (AI) machine. It differs from the Perceptron which is a software architecture proposed in 1943 by Warren McCulloch and Walter Pitts, which was also employed in Mark I, and enhancements of which have continued to be an integral part of cutting edge AI technologies like the Transformer. == Architecture == The Mark I Perceptron was organized into three layers: A set of sensory units which receive optical input A set of association units, each of which fire based on input from multiple sensory units A set of response units, which fire based on input from multiple association units The connection between sensory units and association units were random. The working of association units was very similar to the response units. Different versions of the Mark I used different numbers of units in each of the layers. == Capabilities == In his 1957 proposal for funding for development of the "Cornell Photoperceptron", Rosenblatt claimed:"Devices of this sort are expected ultimately to be capable of concept formation, language translation, collation of military intelligence, and the solution of problems through inductive logic."With the first version of the Mark I Perceptron as early as 1958, Rosenblatt demonstrated a simple binary classification experiment, namely distinguishing between sheets of paper marked on the right versus those marked on the left side. One of the later experiments distinguished a square from a circle printed on paper. The shapes were perfect and their sizes fixed; the only variation was in their position and orientation. The Mark I Perceptron achieved 99.8% accuracy on a test dataset with 500 neurons in a single layer. The size of the training dataset was 10,000 example images. It took 3 seconds for the training pipeline to go through a single image. Higher accuracy was observed with thick outline figures compared to solid figures, likely because outline figures reduced overfitting. Another experiment distinguished between a square and a diamond for which 100% accuracy was achieved with only 60 training images, with a Perceptron having 1,000 neurons in a single layer. The time taken to process each training input for this larger perceptron was 15 seconds. The only variation was in position of the image, since rotation would have been ambiguous. In that same experiment, it could distinguish between the letters X and E with 100% accuracy when trained with only 20 images (10 images of each letter). Variations in the images included both position and rotation by up to 30 degrees. When variation in rotation was increased to any angle (both in training and test datasets), the accuracy reduced to 90% with 60 training images (30 images of each letter). For distinguishing between the letters E and F, a more challenging problem due to their similarity, the same 1,000 neuron perceptron achieved an accuracy of more than 80% with 60 training images. Variation was only in the position of the image, with no rotation.
Application software
Application software is software that is intended for end-user use – not operating, administering or programming a computer. It includes programs such as word processors, web browsers, media players, and mobile applications used in daily tasks. An application (app, application program, software application) is any program that can be categorized as application software. Application is a subjective classification that is often used to differentiate from system and utility software. Application software represents the user-facing layer of computing systems, designed to translate complex system capabilities into task-oriented, goal-driven workflows. Unlike system software, which focuses on hardware orchestration and resource management, application software is centered on problem abstraction, user interaction, and domain-specific functionality. The abbreviation app became popular with the 2008 introduction of the iOS App Store, to refer to applications for mobile devices such as smartphones and tablets. Later, with the release of the Mac App Store in 2010 and the Windows Store in 2011, it began to be used to refer to end-user software in general, regardless of platform. Applications may be bundled with the computer and its system software or published separately. Applications may be proprietary or open-source. == Terminology == === Meaning program and software === When used as an adjective, application can have a broader meaning than that described in this article. For example, concepts such as application programming interface (API), application server, application virtualization, application lifecycle management and portable application refer to programs and software in general. === Distinction between system and application software === The distinction between system and application software is subjective and has been the subject of controversy. For example, one of the key questions in the United States v. Microsoft Corp. antitrust trial was whether Microsoft's Internet Explorer web browser was part of its Windows operating system or a separate piece of application software. As another example, the GNU/Linux naming controversy is, in part, due to disagreement about the relationship between the Linux kernel and the operating systems built over this kernel. In some types of embedded systems, the application software and the operating system software may be indistinguishable by the user, as in the case of software used to control a VCR, DVD player, or microwave oven. The above definitions may exclude some applications that may exist on some computers in large organizations. For an alternative definition of an app: see Application Portfolio Management. === Killer application === A killer application (killer app, coined in the late 1980s) is an application that is so popular that it causes demand for its host platform to increase. For example, VisiCalc was the first modern spreadsheet software for the Apple II and helped sell the then-new personal computers into offices. For the BlackBerry, it was its email software. === Software suite === As software suite consists of multiple applications bundled together. They usually have related functions, features, and user interfaces, and may be able to interact with each other, e.g. open each other's files. Business applications often come in suites, e.g. Microsoft Office, LibreOffice and iWork, which bundle together a word processor, a spreadsheet, etc.; but suites exist for other purposes, e.g. graphics or music. == Ways to classify == As there so many applications and since their attributes vary so dramatically, there are many different ways to classify them. === By legal aspects === Proprietary software is protected under an exclusive copyright, and a software license grants limited usage rights. Such applications may allow add-ons from third parties. Free and open-source software (FOSS) can be run, distributed, sold, and extended for any purpose. FOSS software released under a free license may be perpetual and also royalty-free. Perhaps, the owner, the holder or third-party enforcer of any right (copyright, trademark, patent, or ius in re aliena) are entitled to add exceptions, limitations, time decays or expiring dates to the license terms of use. Public-domain software is a type of FOSS that is royalty-free and can be run, distributed, modified, reversed, republished, or created in derivative works without any copyright attribution and therefore revocation. It can even be sold, but without transferring the public domain property to other single subjects. Public-domain software can be released under a (un)licensing legal statement, which enforces those terms and conditions for an indefinite duration (for a lifetime, or forever). === By platform === An application can be categorized by the host platform on which it runs. Notable platforms include operating system (native), web browser, cloud computing and mobile. For example a web application runs in a web browser whereas a more traditional, native application runs in the environment of a computer's operating system. There has been a contentious debate regarding web applications replacing native applications for many purposes, especially on mobile devices such as smartphones and tablets. Web apps have indeed greatly increased in popularity for some uses, but the advantages of applications make them unlikely to disappear soon, if ever. Furthermore, the two can be complementary, and even integrated. === Horizontal vs. vertical === Application software can be seen as either horizontal or vertical. Horizontal applications are more popular and widespread, because they are general purpose, for example word processors or databases. Vertical applications are niche products, designed for a particular type of industry or business, or department within an organization. Integrated suites of software will try to handle every specific aspect possible of, for example, manufacturing or banking worker, accounting, or customer service. === By purpose === There are many types of application software: Enterprise Addresses the needs of an entire organization's processes and data flows, across several departments, often in a large distributed environment. Examples include enterprise resource planning systems, customer relationship management (CRM) systems, data replication engines, and supply chain management software. Departmental Software is a sub-type of enterprise software with a focus on smaller organizations or groups within a large organization. (Examples include travel expense management and IT Helpdesk.) Enterprise infrastructure Provides common capabilities needed to support enterprise software systems. (Examples include databases, email servers, and systems for managing networks and security.) Application platform as a service (aPaaS) A cloud computing service that offers development and deployment environments for application services. Knowledge worker Lets users create and manage information, often for and individual media editors may aid in multiple information worker tasks. Content access Used primarily to access content without editing, but may include software that allows for content editing. Such software addresses the needs of individuals and groups to consume digital entertainment and published digital content. (Examples include media players, web browsers, and help browsers.) Educational Related to content access software, but has the content or features adapted for use by educators or students. For example, it may deliver evaluations (tests), track progress through material, or include collaborative capabilities. Simulation Simulates physical or abstract systems for either research, training, or entertainment purposes. Media development Generates print and electronic media for others to consume, most often in a commercial or educational setting. This includes graphic-art software, desktop publishing software, multimedia development software, HTML editors, digital-animation editors, digital audio and video composition, and many others. Engineering Used in developing hardware and software products. This includes computer-aided design (CAD), computer-aided engineering (CAE), computer language editing and compiling tools, integrated development environments, and application programmer interfaces. Entertainment Refers to video games, screen savers, programs to display motion pictures or play recorded music, and other forms of entertainment which can be experienced through the use of a computing device. == Taxonomy == This section is a taxonomy of kinds of applications. This organization is but one of many different ways to organize them. A kind is included in only one category even if it logically fits in multiple. === General-purpose === Calculator Spreadsheet Web browser Web mapping E-commerce Social media === Communication === Chat Email Presentation software Phone Messages Networking software Web conferencing === Documentation === Desktop
Deep learning speech synthesis
Deep learning speech synthesis refers to the application of deep learning models to generate natural-sounding human speech from written text (text-to-speech) or spectrum (vocoder). Deep neural networks are trained using large amounts of recorded speech and, in the case of a text-to-speech system, the associated labels and/or input text. == Formulation == Given an input text or some sequence of linguistic units Y {\displaystyle Y} , the target speech X {\displaystyle X} can be derived by X = arg max P ( X | Y , θ ) {\displaystyle X=\arg \max P(X|Y,\theta )} where θ {\displaystyle \theta } is the set of model parameters. Typically, the input text will first be passed to an acoustic feature generator, then the acoustic features are passed to the neural vocoder. For the acoustic feature generator, the loss function is typically L1 loss (Mean Absolute Error, MAE) or L2 loss (Mean Square Error, MSE). These loss functions impose a constraint that the output acoustic feature distributions must be Gaussian or Laplacian. In practice, since the human voice band ranges from approximately 300 to 4000 Hz, the loss function will be designed to have more penalty on this range: l o s s = α loss human + ( 1 − α ) loss other {\displaystyle loss=\alpha {\text{loss}}_{\text{human}}+(1-\alpha ){\text{loss}}_{\text{other}}} where loss human {\displaystyle {\text{loss}}_{\text{human}}} is the loss from human voice band and α {\displaystyle \alpha } is a scalar, typically around 0.5. The acoustic feature is typically a spectrogram or Mel scale. These features capture the time-frequency relation of the speech signal, and thus are sufficient to generate intelligent outputs. The Mel-frequency cepstrum feature used in the speech recognition task is not suitable for speech synthesis, as it reduces too much information. == History == In September 2016, DeepMind released WaveNet, which demonstrated that deep learning-based models are capable of modeling raw waveforms and generating speech from acoustic features like spectrograms or mel-spectrograms. Although WaveNet was initially considered to be computationally expensive and slow to be used in consumer products at the time, a year after its release, DeepMind unveiled a modified version of WaveNet known as "Parallel WaveNet," a production model 1,000 faster than the original. This was followed by Google AI's Tacotron 2 in 2018, which demonstrated that neural networks could produce highly natural speech synthesis but required substantial training data—typically tens of hours of audio—to achieve acceptable quality. Tacotron 2 used an autoencoder architecture with attention mechanisms to convert input text into mel-spectrograms, which were then converted to waveforms using a separate neural vocoder. When trained on smaller datasets, such as 2 hours of speech, the output quality degraded while still being able to maintain intelligible speech, and with just 24 minutes of training data, Tacotron 2 failed to produce intelligible speech. In 2019, Microsoft Research introduced FastSpeech, which addressed speed limitations in autoregressive models like Tacotron 2. FastSpeech utilized a non-autoregressive architecture that enabled parallel sequence generation, significantly reducing inference time while maintaining audio quality. Its feedforward transformer network with length regulation allowed for one-shot prediction of the full mel-spectrogram sequence, avoiding the sequential dependencies that bottlenecked previous approaches. The same year saw the release of HiFi-GAN, a generative adversarial network (GAN)-based vocoder that improved the efficiency of waveform generation while producing high-fidelity speech. In 2020, the release of Glow-TTS introduced a flow-based approach that allowed for fast inference and voice style transfer capabilities. In March 2020, the free text-to-speech website 15.ai was launched. 15.ai gained widespread international attention in early 2021 for its ability to synthesize emotionally expressive speech of fictional characters from popular media with minimal amount of data. The creator of 15.ai (known pseudonymously as 15) stated that 15 seconds of training data is sufficient to perfectly clone a person's voice (hence its name, "15.ai"), a significant reduction from the previously known data requirement of tens of hours. 15.ai is credited as the first platform to popularize AI voice cloning in memes and content creation. 15.ai used a multi-speaker model that enabled simultaneous training of multiple voices and emotions, implemented sentiment analysis using DeepMoji, and supported precise pronunciation control via ARPABET. The 15-second data efficiency benchmark was later corroborated by OpenAI in 2024. == Semi-supervised learning == Currently, self-supervised learning has gained much attention through better use of unlabelled data. Research has shown that, with the aid of self-supervised loss, the need for paired data decreases. == Zero-shot speaker adaptation == Zero-shot speaker adaptation is promising because a single model can generate speech with various speaker styles and characteristic. In June 2018, Google proposed to use pre-trained speaker verification models as speaker encoders to extract speaker embeddings. The speaker encoders then become part of the neural text-to-speech models, so that it can determine the style and characteristics of the output speech. This procedure has shown the community that it is possible to use only a single model to generate speech with multiple styles. == Neural vocoder == In deep learning-based speech synthesis, neural vocoders play an important role in generating high-quality speech from acoustic features. The WaveNet model proposed in 2016 achieves excellent performance on speech quality. Wavenet factorised the joint probability of a waveform x = { x 1 , . . . , x T } {\displaystyle \mathbf {x} =\{x_{1},...,x_{T}\}} as a product of conditional probabilities as follows p θ ( x ) = ∏ t = 1 T p ( x t | x 1 , . . . , x t − 1 ) {\displaystyle p_{\theta }(\mathbf {x} )=\prod _{t=1}^{T}p(x_{t}|x_{1},...,x_{t-1})} where θ {\displaystyle \theta } is the model parameter including many dilated convolution layers. Thus, each audio sample x t {\displaystyle x_{t}} is conditioned on the samples at all previous timesteps. However, the auto-regressive nature of WaveNet makes the inference process dramatically slow. To solve this problem, Parallel WaveNet was proposed. Parallel WaveNet is an inverse autoregressive flow-based model which is trained by knowledge distillation with a pre-trained teacher WaveNet model. Since such inverse autoregressive flow-based models are non-auto-regressive when performing inference, the inference speed is faster than real-time. Meanwhile, Nvidia proposed a flow-based WaveGlow model, which can also generate speech faster than real-time. However, despite the high inference speed, parallel WaveNet has the limitation of needing a pre-trained WaveNet model, so that WaveGlow takes many weeks to converge with limited computing devices. This issue has been solved by Parallel WaveGAN, which learns to produce speech through multi-resolution spectral loss and GAN learning strategies.