Documente Academic
Documente Profesional
Documente Cultură
Artificial Intelligence is the field of study that seeks to explain and emulate intelligent behavior in terms of computational processes. Artificial Intelligence is about generating representations and procedures that automatically or autonomously solve problems heretofore solved by humans.
The simulation of human intelligence on a machine so as to make the machine efficient to identify and use the right piece of knowledge at a given step of solving a problem. A system capable of planning and executing the right task at the right time is generally called rational. While there is no universally accepted definition of intelligence. AI researchers have studied several traits that are considered essential.
Default reasoning and the qualification problem: Many of the things people know take
the form of "working assumptions." For example, if a bird comes up in conversation, people typically picture a animal that is fist sized, sings, and flies. None of these things are true about birds in general. John McCarthy identified this problem in 1969 [46] as the qualification
The breadth of common sense knowledge: The number of atomic facts that the average
person knows is astronomical. Research projects that attempt to build a complete knowledge base of commonsense knowledge, such as CYC, require enormous amounts of tedious stepby-step ontological engineering they must be built, by hand, one complicated concept at a time.
Intelligent agents must be able set goals and achieve them. [49] They need a way to visualize the future: they must have a representation of the state of the world and be able to make predictions about how their actions will change it. There are several types of planning problems: Classical planning problems assume that the agent is the only thing acting on the world, and that the agent can be certain what the consequences of it's actions may be. Partial order planning problems take into account the fact that sometimes it's not important which sub-goal the agent achieves first. If the environment is changing, or if the agent can't be sure of the results of its actions, it must periodically check if the world matches its predictions (conditional planning and execution monitoring) and it must change its plan as this becomes necessary (replanning and continuous planning). Some planning problems take into account the utility or "usefulness" of a given outcome. These problems can be analyzed using tools drawn from economics, such as decision theory or decision analysis[53] and information value theory. Multi-agent planning problems try to determine the best plan for a community of agents, using cooperation and competition to achieve a given goal. These problems are related to emerging fields like evolutionary algorithms and swarm intelligence.
Learning
machine learning Important machine learning problems are: Unsupervised learning: find a model that matches a stream of input "experiences", and be able to predict what new "experiences" to expect. Supervised learning, such as classification (be able to determine what category something belongs in, after being a number of examples of things from each category), or regression (given a set of numerical input/output examples, discover a continuous function that would generate the outputs from the inputs).
List of applications
Typical problems to which AI methods are applied Pattern recognition Optical character recognition Handwriting recognition Speech recognition Face recognition Artificial Creativity Computer vision, Virtual reality and Image processing Diagnosis (artificial intelligence) Game theory and Strategic planning Game artificial intelligence and Computer game bot Natural language processing, Translation and Chatterbots Non-linear control and Robotics
Other fields in which AI methods are implemented Artificial life Automated reasoning Automation Biologically-inspired computing Colloquis Concept mining Data mining Knowledge representation Semantic Web E-mail spam filtering Robotics 5
Assignment no: 1 compiled by D.Prabhu M.Tech CSE www.datatycoon.blogspot.com Behavior-based robotics Cognitive Cybernetics Developmental robotics Epigenetic robotics Evolutionary robotics Hybrid intelligent system Intelligent agent Intelligent control Litigation Swarm Intelligence
SWARM INTELLIGENCE
Swarm intelligence is the term used to denote artificial intelligence systems where collective behavior of simple agents causes coherent solutions or patterns to emerge. This has applications in swarm robotics. A population of unsophisticated agents interacting with their environments and each other makes up a swarm intelligence system. Because there is no set of global instructions on how these units act, the collective interactions of all the agents within the system often leads into some sort of collective behavior or intelligence. This type of artificial intelligence is used to explore distributed problem solving without having a centralized control structure. This is seen to be a better alternative to centralized, rigid and preprogrammed control. Real life swarm intelligence can be observed in ant colonies, beehives bird flocks and animal herds.
Particle swarm optimization Particle swarm optimization, on the other hand, is a type of swarm intelligence inspired by bird flocks and fish schools. This type of swarm optimization gives individual agents within the swarm the ability to change its position depending on its own limited intelligence and in comparison to other agents in the population. This enables individual agents to modify their paths depending on the success of the other agents in the population in finding the correct solution. This type of swarm intelligence is used in practical applications such as in artificial neural networks and in grammatical evolution models. A CHRONOLOGY OF ARTIFICIAL INTELLIGENCE ~3000BC A papyrus which was brought in a Luxor antique shop by Edwin smith in1882 was prepared Representing 48 surgical observations of head wounds. The observations were started in Symptomdiagnosistreatmentprognosis combination as: IF a patient has this symptom THEN he has this injury with this prognosis if this treatment is applied. This is the first known expert system. 13th century Ramn Lull invented the Zairja, the first device that generated ideas by mechanical means. 1651 Leviathan, written by Thomas Hobbes (1588-1679) was published. In it he proposes that humans collectively, by virtue of their organization and use of their machines. Would create a new intelligence. George B. dyson refers to Hobbes as the patriarch of artificial intelligence in his book Darwin among the machines: The evolution of global intelligence p7, 1997. 17th century Leibnitz and Pascal invented mechanical computing devices. Pascal invented an eight digit calculator, the Pascaline in 1642.In 1694 Gottfried Leibnitz computer, which multiplied by repetitive addition an algorithm still in use. 1726 Jonathan Swift anticipated an automatic book writer in Gullivers Travels. 1805 Joseph Marie invented the first truly programmable device to drive looms with instructions provided by punched cards. 1832 Charles Babbage designed the analytical engine a mechanical programmable computer. he had earlier designed a more limited difference engine in 1822 which he never finished building.
1847 George Boole developed a mathematical symbolic logic later called Boolean algebra .For reasoning about categories (i.e. sets of objects), which is also applicable to manipulating and simplifying logical propositions. 1879 Gottlob frege went beyond Boole in his treatment of logic with his invention of predicate logic making it possible to prove general theorems fro rules. ~1890 Hand driven mechanical calculators became available. 1890 Herman Hollerith patented a tabulating machine to process census data fed in on punched cards. his company the tabulating machine company, eventually merged into what was to become IBM Late 1800s Leonardo Torres Y Quevedo invented a relay activated automation that played end games in chess. 1898 Behaviorism was expounded by psychologist Edward Thorndike in Animal Intelligence. The basic idea is that all actions, thoughts, or desires are reflexes triggered by a higher form of stimulus with humans just reacting to a higher form of stimulus. 1921 Karel capek a Czech writer, invented the term ROBOT to describe intelligent machines that revolted against their human masters and destroyed them. 1928 John Von Neumann introduced the minmax theorem which is still used as a basis of game playing program. 1937 Alan Turing conceived of a universal Turing machine that could mimic the operation of any other computing machine. However as did Godel he also recognized that there exists certain kind of calculations that no machine could perform. Even recognizing this limit on computers Turing still did not doubt that computers could be made to think.
~1938 Claude Shannon showed that calculations could be performed much faster using electromagnetic relays than they could be performed with mechanical calculators .he applied Boolean algebra. 1943 Vacuum tubes replaced electromechanical relays in calculators. These were used in 1943 in colossus a faster successor of Robinson, to decipher increasingly complex German codes. 1945 ENIAC (Electronic Numerical Integrator and calculator) which was run 1000 times faster than the relay operated computers was ready to run late 1945 1945 Symbolic artificial intelligence emerged as a specific intellectual field. Key development included Norbert wieners development of the field of cybernetics, in which he invented a mathematical theory of feedback in biological and engineered systems. 1947 The transistor was invented by William Shockley, Walter Brattain and John Bardeen. 1948 Norbert Wiener published cybernetics a landmark book on information theory. Cybernetics means the science of control and communication in the animal and the machine. 1949 Donald O. Hebbs suggested a way in which artificial neural networks might learn. 1950 Turing proposed his test the Turing test, to recognize machine intelligence. 1950s It became clear that computers could manipulate symbols representing concepts as well as numerical data. 1951 EDVAC, the first Von Neumann computer, was built. 1951
10
11
12
1973 Sir James Light hill, Cambridge Universitys Lucasian Chair of Applied Mathematics, advised the British government to cease most AI research in Britain. 1974 Funding for AI research at MIT ,Carnegie Mellon , and Stanford from DARPA was cut drastically as a result of recent disappointing results . Diverging Specialities in AI field emerged these include Edward Feigenbaums work on expert systems ;Roger Shank on language analysis ;Marvin Minsky on knowledge representation;Douglas lenat on automatic learning and nature of heuristics ;david marr on machine vision; and others developing PROLOG. 1975 Marvin Minsky published a paper , a framework for representing knowledge , which he started withit seems to me that the ingredients of most theories in artificial intelligence and in psychology have been on the whole too minute ,local and unstructured to account for the effectiveness of commonsense thought. ~1977 Roger Schank and others augmented the conceptual dependency theory with the use of scripts and the use of knowledge of peoples plans and goals to make sense of stories told by people and to answer questions about those stories that would require inferences to be made to answer them. First commercial expert system developed was XCON (for eXpert CONfigurer), developed by John McDermott at Carnegie Mellon. July 1979 World Champion backgammon player, Luigi Villa of Italy became the first human champion of a board game to be defeated by a computer program, which was written by Hans Berliner of Carnegie Mellon. The program evaluated its moves by evaluating a weighted set of criteria that measured the goodness of a move. 1980s Fuzzy Logic was introduced in a fuzzy predictive system used to operate the automated subway trains in sendai, Japan. This system, designed by Hitachi, reduced energy consumption by 10% and lowered the margin of error in stopping the trains at specified positions to less than 10 centimeters. First meeting of the American Association for Artificial Intelligence held in Stanford, California. 1982
13
Early and mid 1980s A succession of early expert systems were built and put in use by companies these included: A hydrostatic and rotary bacteria Killing cooker diagnosis program at Campbells Soup based on Aldo Ciminos Knowledge; A lathe & grinder diagnosis analyzer at GMs Saginaw plant using Charlie Ambles skills at listening for problems based on sounds; A mineral prospecting expert system called PROSPECTOR that found a molybdenum deposit. A bell system that analyzed problems in telephone networks & recommended solutions. FOLIO an investment portfolio advisor; WILLIARD , a forecaster of large thunderstorms. Mid 1980s Resurgence of neural network technology with the publication of key papers by the Parallel Distributed Processing Study Group. Demonstrations of neural networks in diverse applications such as artificial speech generation, learning to play backgammon, and driving a vehicle illustrated the versatility of the technology. 1985 MITs Media Laboratory, Dedicated to researching media related applications using computer science (including artificial intelligence) and sociology, was found under jerome weisner and Nicholas Negroponte. Speech systems are now able to provide any of the following: a large vocabulary, continuous speech recognition or speaker independence. 1987 Etienne Wenger published his book ARTIFICIAL INTELLIGENCE & TUTORING SYSTEMS: Computational & Cognitive Approaches to the Communication of Knowledge, a milestone in the development of intelligent tutoring systems. Inflexibility of these expert systems in applying rules and the tunnel vision implied in their limited knowledge can result in poor conclusions. Expert Systems couldnt reverse their logical conclusions if later given contradictory facts. End of 1980s Experts systems were increasingly used in industry, and other AI techniques were being implemented jointly with conventional software, often unnoticed but with beneficial effect. 1990s
14
[6] The Winchester- vol2, p12-15, published by dept of computer science, B.C.E.T Karaikal
15