Unformatted text preview: Lecture 1 Introduction to knowledge-base Introduction intelligent systems intelligent Intelligent machines, or what machines can do Intelligent The history of artificial intelligence or from the “Dark Ages” to knowledge-based systems systems Summary Summary 1 Intelligent machines, or what Intelligent machines can do Philosophers have been trying for over 2000 years to understand and resolve two Big Questions of the Universe: How does a human mind work, and Can non-humans have minds? These questions are still unanswered. are Intelligence is the ability to understand and learn things. 2 Intelligence is the ability to think and understand instead of doing things by instinct or automatically. automatically. (Essential English Dictionary, Collins, London, 1990)
2 In order to think, someone or something has to have In one or thing a brain, or an organ that enables someone or brain, one something to learn and understand things, to solve something problems and to make decisions. So we can define intelligence as the ability to learn and understand, intelligence to solve problems and to make decisions. The goal of artificial intelligence (AI) as a science is to make machines do things that would require intelligence if done by humans. Therefore, the answer to the question Can Machines Think? was vitally important to the discipline. vitally The answer is not a simple “Yes” or “ No ”. The or ”.
3 Some people are smarter in some ways than others. Some Sometimes we make very intelligent decisions but sometimes we also make very silly mistakes. Some of us deal with complex mathematical and engineering problems but not in philosophy and history. history. Our abilities are not equal and lie in different areas. Our Therefore, we should expect that if machines can think, some of them might be smarter than others in some ways. in 4 One of the most significant papers on machine intelligence, “Computing Machinery and Intelligence”, was written by the British Intelligence” was mathematician Alan Turing over fifty years ago. However, it still stands up well under the test of time, and the Turing’s approach remains universal. universal. He asked: Can machines think? He Can
Turing did not provide definitions of machines and thinking, he Turing just avoided semantic arguments by inventing a game, the Turing Imitation Game. Turing
5 Turing Imitation Game: Phase 1 6 Turing Imitation Game: Phase 1 Turing The imitation game originally included two phases. In the first phase, the interrogator, a man and a woman are each placed in separate rooms. The interrogator’s objective is to work out who is the man and who is the woman by questioning them. The man should attempt to deceive the interrogator that he is the woman, while the woman has to convince the interrogator that she is the woman. is 7 Turing Imitation Game: Phase 2 8 Turing Imitation Game: Phase 2 Turing In the second phase of the game, the man is replaced by a computer programmed to deceive the interrogator as the man did. It would even be programmed to make mistakes and provide fuzzy answers in the way a human would. If the computer can fool the interrogator as often as the man did, we may say this computer has passed the intelligent behaviour test. the 9 A program thought intelligent by comparing its program performance with the performance of a human expert. expert. To build an intelligent computer system, we have to To capture, organise and use human expert knowledge in some narrow area of expertise. in 10 The history of artificial intelligence
The birth of artificial intelligence (1943 – 1956) The first work recognised in the field of AI was The presented by Warren McCulloch and Walter Pitts in 1943. They proposed a model of an in hey artificial neural network and demonstrated that artificial simple network structures could learn. simple 11 The third founder of AI was John von Neumann, The John the brilliant Hungarian-born mathematician. He was influenced by McCulloch and Pitts’s neural network model. When Marvin Minsky and Dean Edmonds, two graduate students in the Princeton Edmonds two mathematics department, built the first neural network computer in 1951, von Neumann network encouraged and supported them. encouraged 12 Another of the first generation researchers was Another Claude Shannon. Shannon shared Alan Turing’s Claude Shannon ideas on the possibility of machine intelligence. In 1950, he published a paper on chess-playing machines, which pointed out that a typical chess game involved about 10120 possible moves 10 (Shannon, 1950). Thus Shannon demonstrated the need to use heuristics in the search for the solution. need 13 In 1956, John McCarthy, Martin Minsky and In John Claude Shannon organised a summer workshop at Dartmouth College. They brought together Dartmouth researchers interested in the study of machine intelligence, artificial neural nets and automata theory. Although there were just ten researchers, this workshop gave birth to a new science called artificial intelligence. artificial 14 The rise of artificial intelligence, or the era of The great expectations (1956 – late 1960s) great Great expectations during 1950s and 1960s But very limited success Researchers focused too much on allpurpose intelligent machines with goals to learn and reason with human-scale knowledge (and beyond) General Problem Solver (GPS) to simulate human problem solving methods. But now referred as weak methods
15 Difficulties in AI in 1960’s Because of general methods for broad classes of problems, early programs contains no knowledge about problem domain. Many of problems that attempted are too broad and difficult. Example machine translation ,the translation of Russian scientific papers. British government also suspended support for AI research.
16 Probably the most important development in Probably the seventies was the realisation that the domain for intelligent machines had to be sufficiently restricted. sufficiently Refocus on specific problem domains (1970s) Domain-specific expert systems with facts, Domain-specific expert facts rules, etc. rules
17 The technology of expert systems, or the key The to to success (early 1970s – mid-1980s) success DENDRAL A space craft to be launched to Mars and a program was required to determine the molecular structure of determine soil, based on the mass spectral data provided by a mass spectrometer. mass All possible molecular structures are generated and tested against actual spectrum. But there was no scientific algorithm for mapping the here mass spectrum into its molecular structure. Feigenbaum’s job was to incorporate the expertise into a computer program to make it perform at a human expert level. Such programs were later called expert systems. systems
18 The DENDRAL project originated the fundamental idea The of expert systems – knowledge engineering, which knowledge which encompassed techniques of capturing, analysing and expressing in rules an expert’s “know-how”. expressing 19 MYCIN MYCIN was a rule-based expert system for the MYCIN diagnosis of infectious blood diseases. It also provided a doctor with therapeutic advice in a convenient, user- friendly manner. convenient, MYCIN’s knowledge consisted of about 450 rules MYCIN’s derived from human knowledge in a narrow domain through extensive interviewing of experts. experts. 20 However: Expert systems are restricted to a very narrow Expert domain of expertise. For example, MYCIN, which was developed for the diagnosis of infectious blood diseases, lacks any real knowledge of human physiology. If a patient has more than one disease, we cannot rely on MYCIN. Expert systems have difficulty in recognising domain Expert boundaries. Expert systems, especially the first generation, have Expert little or no ability to learn from their experience. Expert systems are built individually and cannot be developed fast. 21 How to make a machine learn, or the rebirth of neural networks (mid-1980s – onwards) neural In the mid-eighties, researchers, engineers and In experts found that building an expert system required much more than just buying a reasoning system or expert system shell and putting enough rules in it. Disillusions about the applicability of expert system Disillusions technology even led to people predicting an 6 hswdÌ with severely squeezed funding for AI projects. AI researchers decided to have a new look at neural networks. at
22 By the late sixties, most of the basic ideas and By concepts necessary for neural computing had already been formulated. However, only in the mid-eighties did the solution emerge. The major reason for the delay was technological: there were no PCs or powerful workstations to model and experiment with artificial neural networks. experiment Artificial neural networks may either be used to gain an understanding of biological neural networks, or for solving artificial intelligence problems without necessarily creating a model of a real biological system necessarily
23 The new era of knowledge engineering, or computing with words (late 1980s – onwards) However, neural networks lack explanation facilities However, and usually act as a black box. The process of training neural networks with current technologies is slow, and frequent retraining can cause serious difficulties. difficulties. 24 Very important technology dealing with vague, Very imprecise and uncertain knowledge and data is fuzzy logic. logic Fuzzy logic is concerned with capturing the meaning Fuzzy of words, human reasoning and decision making. Fuzzy logic provides the way to break through the computational bottlenecks of traditional expert systems. systems. At the heart of fuzzy logic lies the concept of a At linguistic variable. The values of the linguistic linguistic The variable are words rather than numbers. variable
It has been used successfully since 1987 in Japanese- designed dishwashers, washing machines, air conditioners, television sets, copiers, and even cars. copiers,
25 Benefits derived from the application of fuzzy logic models in knowledge-based can be logic summarised as follows: summarised Improved computational power: Fuzzy ruleImproved Fuzzy based systems perform faster than conventional based expert systems and require fewer rules. A fuzzy expert expert system merges the rules, making them more powerful. 26 Improved cognitive modelling: Fuzzy systems allow Improved the encoding of knowledge in a form that reflects the way experts think about a complex problem. They usually think in such imprecise terms as high and low, low fast and slow, heavy and light. slow light In contrast, fuzzy expert systems model imprecise In information, capturing expertise similar to the way it is represented in the expert mind, and thus improve cognitive (psychological result of perception and learning and cognitive psychological reasoning) modelling of the problem. reasoning
27 The ability to represent multiple experts: When a more complex expert system is being built or when expertise is not well defined, multiple experts might be needed. Fuzzy expert systems can help to represent the expertise of multiple experts when they have opposing views. views. 28 Summary Expert, neural and fuzzy systems have now Expert, matured and been applied to a broad range of different problems, mainly in engineering, medicine, finance, business and management. medicine, Each technology handles the uncertainty and Each ambiguity of human knowledge differently, and each technology has found its place in knowledge engineering. They no longer compete; rather they complement each other. complement 29 Main events in the history of AI
The birth of Ar tificial Intelligence (1943–1956) Key Events
McCulloch and Pitts, A Logical Calculus of the Ideas Immanent in Nervous Activity, 1943 Turing, Computing Machinery and Intelligence, 1950 The Electronic Numerical Integrator and Calculator project (von Neumann) Shannon, Programming a Computer for Playing Chess, 1950 The Dartmouth College summer workshop on machine intelligence, artificial neural nets and automata theory, 1956 30 Period
The discovery of expert systems (early 1970s–mid-1980s) Key Events
DENDRAL (Feigenbaum, Buchanan and Lederberg, Stanford University) MYCIN (Feigenbaum and Shortliffe, Stanford University) PROSPECTOR (Stanford Research Institute) PROLOG - a logic programming language (Colmerauer, Roussel and Kowalski, France) EMYCIN (Stanford University) Waterman, A Guide to Expert Systems, 1986 31 Period
The rebirth of artificial neural networks (1965–onwards) Key Events
Hopfield, Neural Networks and Physical Systems with Emergent Collective Computational Abilities, 1982 Kohonen, Self-Organized Formation of Topologically Correct Feature Maps, 1982 Rumelhart and McClelland, Processing, 1986 Parallel Distributed The First IEEE International Conference on Neural Networks, 1987 Haykin, Neural Networks, 1994 Neural Network, MATLAB Application Toolbox (The MathWork, Inc.) 32 Period
Evolutionary computation (early 1970s–onwards) Key Events
Rechenberg, Evolutionsstrategien - Optimierung Technischer Systeme Nach Prinzipien der Biologischen Information, 1973 Holland, Adaptation in Natural and Artificial Systems, 1975. Koza, Genetic Programming: On the Programming of the Computers by Means of Natural Selection, 1992. Schwefel, Evolution and Optimum Seeking, 1995
Fogel, Evolutionary Computation –Towards a New Philosophy of Machine Intelligence, 1995. 33 Period Key Events Computing with Zadeh, Fuzzy Sets , 1965 Words Zadeh, Fuzzy Algorithms, 1969 (late 1980s–onwards) Mamdani, Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis, 1977 Sugeno, Fuzzy Theory, 1983 Japanese “fuzzy” consumer products (dishwashers, washing machines, air conditioners, television sets, copiers) Sendai Subway System (Hitachi, Japan), 1986 The First IEEE International Conference on Fuzzy Systems, 1992 Kosko, Neural Networks and Fuzzy Systems, 1992 Kosko, Fuzzy Thinking, 1993 Cox, The Fuzzy Systems Handbook, 1994 Zadeh, Computing with Words - A Paradigm Shift , 1996 Fuzzy Logic, MATLAB Application Toolbox (The MathWork, Inc.) 34 ...
View Full Document
This note was uploaded on 01/04/2010 for the course MSC CP 1312 taught by Professor Ms.nireshfathima during the Fall '09 term at Unity.
- Fall '09