正在生成预览...
Lecture 1Lecture 1 Introduction to knowledge-baseIntroduction to knowledge-base intelligent systemsintelligent systems Intelligent machinesIntelligent machines, or, or whatwhat machinesmachines cancan dodo The historyThe history ofof artificialartificial intelligenceintelligence oror fromfrom thethe “Dark Ages” to knowledge“Dark Ages” to knowledge--based systemsbased systems SummarySummary Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 1
Intelligent machinesIntelligent machines, or, or whatwhat machines canmachines can dodo Philosophers have been trying for over 2000 yearsPhilosophers have been trying for over 2000 years to understand and resolve twoto understand and resolve two Big QuestionsBig Questions of theof the Universe:Universe: How does a human mind work, andHow does a human mind work, and Can non-humans have minds?Can non-humans have minds? These questionsThese questions are still unanswered.are still unanswered. IntelligenceIntelligence is their ability to understand and learnis their ability to understand and learn things. 2things. 2 IntelligenceIntelligence is the ability to think andis the ability to think and understand instead of doing things by instinct orunderstand instead of doing things by instinct or automatically.automatically. ((Essential English DictionaryEssential English Dictionary, Collins, London, 1990), Collins, London, 1990) Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 2
In order to think, someIn order to think, someoneone or someor somethingthing has to havehas to have a brain, or an organ thata brain, or an organ that enables someenables someoneone oror somesomethingthing to learn and understand things, to solveto learn and understand things, to solve problems and to make decisions. So we can defineproblems and to make decisions. So we can define intelligence asintelligence as the ability to learn and understand,the ability to learn and understand, to solve problems and to make decisionsto solve problems and to make decisions.. The goal ofThe goal of artificial intelligenceartificial intelligence (AI) as a science(AI) as a science is to make machines do things that would requireis to make machines do things that would require intelligence if done by humans. Therefore, theintelligence if done by humans. Therefore, the answer to the questionanswer to the question Can Machines Think?Can Machines Think? waswas vitally important to the discipline.vitally important to the discipline. The answer is not a simple “The answer is not a simple “YesYes” or “” or “NoNo”.”. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 3
Some people are smarter in some ways than others.Some people are smarter in some ways than others. Sometimes we make very intelligent decisions butSometimes we make very intelligent decisions but sometimes we also make very silly mistakes. Somesometimes we also make very silly mistakes. Some of us deal with complex mathematical andof us deal with complex mathematical and engineering problems but are moronic inengineering problems but are moronic in philosophy and history. Some people are good atphilosophy and history. Some people are good at making money, while others are better at spendingmaking money, while others are better at spending it. As humans, we all have the ability to learn andit. As humans, we all have the ability to learn and understand, to solve problems and to makeunderstand, to solve problems and to make decisions; however, our abilities are not equal anddecisions; however, our abilities are not equal and lie in different areas. Therefore, we should expectlie in different areas. Therefore, we should expect that if machines can think, some of them might bethat if machines can think, some of them might be smarter than others in some ways.smarter than others in some ways. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 4
One of the most significantOne of the most significant papers on machinepapers on machine intelligence,intelligence, “Computing Machinery and“Computing Machinery and Intelligence”Intelligence”, was written by the British, was written by the British mathematicianmathematician Alan TuringAlan Turing over fifty years ago .over fifty years ago . However, it still stands up well under the test ofHowever, it still stands up well under the test of time, and the Turing’s approach remains universal.time, and the Turing’s approach remains universal. He asked:He asked: Is there thought without experience? IsIs there thought without experience? Is there mind without communication? Is therethere mind without communication? Is there language without living? Is there intelligencelanguage without living? Is there intelligence without life?without life? All these questions, as you can see,All these questions, as you can see, are just variations on the fundamental question ofare just variations on the fundamental question of artificial intelligence,artificial intelligence, Can machines think?Can machines think? Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 5
Turing did not provide definitions of machines andTuring did not provide definitions of machines and thinking, he just avoided semantic arguments bythinking, he just avoided semantic arguments by inventing a game, theinventing a game, the Turing Imitation GameTuring Imitation Game.. The imitation game originally included two phases.The imitation game originally included two phases. In the first phase, the interrogator, a man and aIn the first phase, the interrogator, a man and a woman are each placed in separate rooms. Thewoman are each placed in separate rooms. The interrogator’s objective is to work out who is theinterrogator’s objective is to work out who is the man and who is the woman by questioning them.man and who is the woman by questioning them. The man should attempt to deceive the interrogatorThe man should attempt to deceive the interrogator thatthat hehe is the woman, while the woman has tois the woman, while the woman has to convince the interrogator thatconvince the interrogator that sheshe is the woman.is the woman. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 6
Turing Imitation Game: Phase 1Turing Imitation Game: Phase 1 Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 7
Turing Imitation Game: Phase 2Turing Imitation Game: Phase 2 In the second phase of the game, the man isIn the second phase of the game, the man is replaced by a computer programmed to deceive thereplaced by a computer programmed to deceive the interrogator as the man did. It would even beinterrogator as the man did. It would even be programmed to make mistakes and provide fuzzyprogrammed to make mistakes and provide fuzzy answers in the way a human would. If theanswers in the way a human would. If the computer can fool the interrogator as often as thecomputer can fool the interrogator as often as the man did, we may say this computer has passed theman did, we may say this computer has passed the intelligent behaviour test.intelligent behaviour test. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 8
Turing Imitation Game: Phase 2Turing Imitation Game: Phase 2 Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 9
The Turing test has two remarkable qualitiesThe Turing test has two remarkable qualities that make it really universal.that make it really universal. By maintaining communication between the humanBy maintaining communication between the human and the machine via terminals, the test gives us anand the machine via terminals, the test gives us an objective standard view on intelligence.objective standard view on intelligence. The test itself is quite independent from the detailsThe test itself is quite independent from the details of the experiment. It can be conducted as a twoof the experiment. It can be conducted as a two-- phase game, or even as a singlephase game, or even as a single-phase game when-phase game when the interrogator needs to choose between thethe interrogator needs to choose between the human and the machine from the beginning of thehuman and the machine from the beginning of the test.test. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 10
Turing believed that by the end of the 20th centuryTuring believed that by the end of the 20th century it would be possible to program a digital computerit would be possible to program a digital computer to play the imitation game. Although modernto play the imitation game. Although modern computers still cannot pass the Turing test, itcomputers still cannot pass the Turing test, it provides a basis for the verification and validationprovides a basis for the verification and validation of knowledge-based systems.of knowledge-based systems. A program thought intelligent in some narrowA program thought intelligent in some narrow area of expertise is evaluated by comparing itsarea of expertise is evaluated by comparing its performance with the performance of a humanperformance with the performance of a human expert.expert. To build an intelligent computer system, we have toTo build an intelligent computer system, we have to capture, organise and use human expert knowledgecapture, organise and use human expert knowledge in some narrow area of expertise.in some narrow area of expertise. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 11
The history of artificial intelligenceThe history of artificial intelligence The birth of artificial intelligence (1943 – 1956)The birth of artificial intelligence (1943 – 1956) The first work recognised in the field of AI wasThe first work recognised in the field of AI was presented bypresented by Warren McCullochWarren McCulloch andand WalterWalter PittsPitts in 1943. Theyin 1943. They proposed a model of anproposed a model of an artificial neuralartificial neural networknetwork andand demonstrateddemonstrated thatthat simple network structures could learn.simple network structures could learn. McCulloch, the second “founding father” of AIMcCulloch, the second “founding father” of AI after Alan Turing, had created the corner stone ofafter Alan Turing, had created the corner stone of neural computing and artificial neural networksneural computing and artificial neural networks (ANN).(ANN). Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 12
The third founder of AI wasThe third founder of AI was John von NeumannJohn von Neumann,, the brilliant Hungarian-born mathematician. Inthe brilliant Hungarian-born mathematician. In 1930, he joined the Princeton University, lecturing1930, he joined the Princeton University, lecturing in mathematical physics. He was an adviser for thein mathematical physics. He was an adviser for the Electronic Numerical Integrator and CalculatorElectronic Numerical Integrator and Calculator project at the University of Pennsylvania andproject at the University of Pennsylvania and helped to design thehelped to design the Electronic Discrete VariableElectronic Discrete Variable CalculatorCalculator. He was influenced by McCulloch and. He was influenced by McCulloch and Pitts’s neural network model. WhenPitts’s neural network model. When MarvinMarvin MinskyMinsky andand Dean EdmondsDean Edmonds, two graduate, two graduate students in the Princeton mathematics department,students in the Princeton mathematics department, built the first neural network computer in 1951, vonbuilt the first neural network computer in 1951, von Neumann encouraged and supported them.Neumann encouraged and supported them. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 13
Another of the first generation researchers wasAnother of the first generation researchers was Claude ShannonClaude Shannon. He graduated from MIT and. He graduated from MIT and joined Bell Telephone Laboratories in 1941.joined Bell Telephone Laboratories in 1941. Shannon shared Alan Turing’s ideas on theShannon shared Alan Turing’s ideas on the possibility of machine intelligence. In 1950, hepossibility of machine intelligence. In 1950, he published a paper on chess-playing machines,published a paper on chess-playing machines, which pointed out that a typical chess gamewhich pointed out that a typical chess game involved about 10involved about 10120120 possible moves (Shannon,possible moves (Shannon, 1950). Even if the new von Neumann1950). Even if the new von Neumann-type-type computer could examine one move percomputer could examine one move per microsecond, it would take 3microsecond, it would take 3 ×× 1010106106 years to makeyears to make its first move. Thus Shannon demonstrated theits first move. Thus Shannon demonstrated the need to use heuristics in the search for the solution.need to use heuristics in the search for the solution. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 14
In 1956,In 1956, John McCarthyJohn McCarthy,, Martin MinskyMartin Minsky andand Claude ShannonClaude Shannon organised a summer workshop atorganised a summer workshop at Dartmouth College. They brought togetherDartmouth College. They brought together researchers interested in the study of machineresearchers interested in the study of machine intelligence, artificial neural nets and automataintelligence, artificial neural nets and automata theory. Although there were just ten researchers,theory. Although there were just ten researchers, this workshop gave birth to a new science calledthis workshop gave birth to a new science called artificial intelligenceartificial intelligence.. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 15
The riseThe rise ofof artificialartificial intelligenceintelligence, or the, or the eraera ofof great expectationsgreat expectations (1956 – late 1960s)(1956 – late 1960s) The early works on neural computing and artificialThe early works on neural computing and artificial neural networks started by McCullochneural networks started by McCulloch andand PittsPitts was continued. Learning methods were improvedwas continued. Learning methods were improved andand Frank RosenblattFrank Rosenblatt proved theproved the perceptronperceptron convergence theoremconvergence theorem, demonstrating that his, demonstrating that his learning algorithm could adjust the connectionlearning algorithm could adjust the connection strengths of a perceptron.strengths of a perceptron. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 16
One of the most ambitious projects of the era ofOne of the most ambitious projects of the era of great expectations was thegreat expectations was the General ProblemGeneral Problem Solver (GPS)Solver (GPS).. Allen NewellAllen Newell andand Herbert SimonHerbert Simon from the Carnegie Mellon University developed afrom the Carnegie Mellon University developed a general-purpose program to simulate human-general-purpose program to simulate human- solving methods.solving methods. Newell and Simon postulated that a problem to beNewell and Simon postulated that a problem to be solved could be defined in terms ofsolved could be defined in terms of statesstates. They. They used the mean-end analysis to determine aused the mean-end analysis to determine a difference between the current and desirable ordifference between the current and desirable or goal stategoal state of the problem, and to choose and applyof the problem, and to choose and apply operatorsoperators to reach the goal state. The set ofto reach the goal state. The set of operators determined the solution plan.operators determined the solution plan. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 17
However, GPS failed to solve complex problems.However, GPS failed to solve complex problems. The program was based on formal logic and couldThe program was based on formal logic and could generate an infinite number of possible operators.generate an infinite number of possible operators. The amount of computer time and memory thatThe amount of computer time and memory that GPS required to solve real-world problems led toGPS required to solve real-world problems led to the project being abandoned.the project being abandoned. In the sixties, AI researchers attempted to simulateIn the sixties, AI researchers attempted to simulate the thinking process by inventingthe thinking process by inventing general methodsgeneral methods for solvingfor solving broad classes of problemsbroad classes of problems. They used. They used the general-purpose search mechanism to find athe general-purpose search mechanism to find a solution to the problem. Such approaches, nowsolution to the problem. Such approaches, now referred to asreferred to as weak methodsweak methods, applied weak, applied weak information about the problem domain.information about the problem domain. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 18
By 1970, the euphoria about AI was gone, and mostBy 1970, the euphoria about AI was gone, and most government funding for AI projects was cancelled.government funding for AI projects was cancelled. AI was still a relatively new field, academic inAI was still a relatively new field, academic in nature, with few practical applications apart fromnature, with few practical applications apart from playing games. So, to the outsider, the achievedplaying games. So, to the outsider, the achieved results would be seen as toys, as no AI system atresults would be seen as toys, as no AI system at that time could manage real-world problems.that time could manage real-world problems. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 19
Unfulfilled promisesUnfulfilled promises, or the, or the impactimpact ofof realityreality (late 1960s – early 1970s)(late 1960s – early 1970s) The main difficulties for AI in the late 1960s were:The main difficulties for AI in the late 1960s were: Because AI researchers were developing generalBecause AI researchers were developing general methods for broad classes of problems, earlymethods for broad classes of problems, early programs contained little or even no knowledgeprograms contained little or even no knowledge about a problem domain. To solve problems,about a problem domain. To solve problems, programs applied a search strategy by trying outprograms applied a search strategy by trying out different combinations of small steps, until the rightdifferent combinations of small steps, until the right one was found. This approach was quite feasible forone was found. This approach was quite feasible for simplesimple toy problemstoy problems, so it seemed reasonable that,, so it seemed reasonable that, if the programs could be “scaled up” to solve largeif the programs could be “scaled up” to solve large problems, they would finally succeed.problems, they would finally succeed. Negnevitsky, Pearson Education, 2002Negnevitsky, Pearson Education, 2002 20
显示前 20 页。下载资料查看完整内容。
暂无评论。快来抢沙发吧！
评论 (0)
暂无评论。快来抢沙发吧！