Скачать презентацию Artificial Intelligence introduction 2 CSE 402 K 3 R Скачать презентацию Artificial Intelligence introduction 2 CSE 402 K 3 R

31e83557c9e271d64d36b8f145719974.ppt

  • Количество слайдов: 15

Artificial Intelligence introduction(2) CSE 402 K 3 R 20/K 3 R 23 Artificial Intelligence introduction(2) CSE 402 K 3 R 20/K 3 R 23

A Brief History of Artificial Intelligence AI has roots in a number of scientific A Brief History of Artificial Intelligence AI has roots in a number of scientific disciplines – computer science and engineering (hardware and software) – philosophy (rules of reasoning) – mathematics (logic, algorithms, optimization) – cognitive science and psychology (modeling high level human/animal thinking) – neural science (model low level human/animal brain activity) – linguistics

A Brief History of Artificial Intelligence The birth of AI (1943 – 1956) – A Brief History of Artificial Intelligence The birth of AI (1943 – 1956) – Pitts and Mc. Culloch (1943): simplified mathematical model of neurons can realize all propositional logic primitives (can compute all Turing computable functions) – Allen Turing: Turing machine and Turing test (1950) – Claude Shannon: information theory; possibility of chess playing computers

A Brief History of Artificial Intelligence Early enthusiasm (1952 – 1969) – 1956 Dartmouth A Brief History of Artificial Intelligence Early enthusiasm (1952 – 1969) – 1956 Dartmouth conference John Mc. Carthy (Lisp); Marvin Minsky (first neural network machine); – Emphasize on intelligent general problem solving Lisp (AI programming language); Resolution by John Robinson (basis for automatic theorem proving); heuristic search (A*, AO*, game tree search)

A Brief History of Artificial Intelligence Emphasis on knowledge (1966 – 1974) – domain A Brief History of Artificial Intelligence Emphasis on knowledge (1966 – 1974) – domain specific knowledge is the key to overcome existing difficulties – knowledge representation (KR) paradigms Knowledge-based systems (1969 – 1999) – DENDRAL: the first knowledge intensive system (determining 3 D structures of complex chemical compounds) – MYCIN: first rule-based expert system (containing 450 rules for diagnosing blood infectious diseases) EMYCIN: an ES shell – PROSPECTOR: first knowledge-based system that made significant profit (geological ES for mineral deposits)

A Brief History of Artificial Intelligence AI became an industry (1980 – 1989) – A Brief History of Artificial Intelligence AI became an industry (1980 – 1989) – wide applications in various domains – commercially available tools Current trends (1990 – present) – more realistic goals – more practical (application oriented) – distributed AI and intelligent software agents – resurgence of neural networks and emergence of genetic algorithms

Programming languages for AI • The relational languages like PROLOG [ PROgramming in LOgic] Programming languages for AI • The relational languages like PROLOG [ PROgramming in LOgic] AND LISP [LISt Processing] in AI. • LISP is well suited for handling lists, where as PROLOG is designed for logic Programming Architecture of AI machine At the early stage of programs of AI, common machine used for conventional programming were also used for AI programming. This special architecture, called LISP and PROLOG machine. Most of this architecture are used in research laboratory, and are not available in the open commercial market.

Possible Approaches Like humans Think Act GPS Well Rational agents AI tends to work Possible Approaches Like humans Think Act GPS Well Rational agents AI tends to work mostly in this area Eliza Heuristic systems

Think well • Develop formal models of knowledge representation, reasoning, learning memory, problem solving, Think well • Develop formal models of knowledge representation, reasoning, learning memory, problem solving, that can be rendered in algorithms. • There is often an emphasis on a systems that are provably correct, and guarantee finding an optimal solution. Like humans Think Act Well GPS Rational agents Eliza Heuristic systems

Act well • For a given set of inputs, generate an appropriate output that Act well • For a given set of inputs, generate an appropriate output that is not necessarily correct but gets the job done. • A heuristic (heuristic rule, heuristic method) is a rule of thumb, strategy, trick, simplification, or any other kind of device which drastically limits search for solutions in large problem spaces. • Heuristics do not guarantee optimal solutions; in fact, they do not guarantee any solution at all: all that can be said for a useful heuristic is that it offers solutions which are good enough most of the time. – Feigenbaum and Feldman, 1963, p. 6 Like humans Think Act Well GPS Rational agents Eliza Heuristic systems

Think like humans • Cognitive science approach • Focus not just on behavior and Think like humans • Cognitive science approach • Focus not just on behavior and I/O but also look at reasoning process. • Computational model should reflect “how” results were obtained. • Provide a new language for expressing cognitive theories and new mechanisms for evaluating them • GPS (General Problem Solver): Goal not just to produce humanlike behavior (like ELIZA), but to produce a sequence of steps of the reasoning process that was similar to the steps followed by a person in solving the same task. Like humans Think Act Well GPS Rational agents Eliza Heuristic systems

Act like humans • Behaviorist approach. • Not interested in how you get results, Act like humans • Behaviorist approach. • Not interested in how you get results, just the similarity to what human results are. • Exemplified by the Turing Test (Alan Turing, 1950). • ELIZA: A program that simulated a psychotherapist interacting with a patient and successfully passed the Turing Test. • Coded at MIT during 1964 -1966 by Joel Weizenbaum. Like humans Think Act Well GPS Rational agents Eliza Heuristic systems

Areas of AI and their inter-dependencies Search Logic Machine Learning NLP Vision Knowledge Representation Areas of AI and their inter-dependencies Search Logic Machine Learning NLP Vision Knowledge Representation Planning Robotics Expert Systems

Branches of AI • • • • Logical AI Search Natural language processing pattern Branches of AI • • • • Logical AI Search Natural language processing pattern recognition Knowledge representation Inference From some facts, others can be inferred. Automated reasoning Learning from experience Planning To generate a strategy for achieving some goal Epistemology This is a study of the kinds of knowledge that are required for solving problems in the world. Genetic programming Emotions? ? ? …

an Th Yo k !! ! u an Th Yo k !! ! u