人工智能英文版.ppt

1、Artificial intelligence,Can it replace a human brain one day?,Artificial intelligence is to use computers to analog and instead of human brain . The advent of computers has made artificial intelligence a major breakthrough. The computer can not only replace some of the human brain function, but exce

2、ed the human brain greatly in speed and accuracy .It can not only simulate part of analysis and the comprehensive function, but is getting to display a certain characteristics of consciousness. It really became an extension of the human brain.,What is AI?,The exciting new effort to make computers th

3、inks machine with minds, in the full and literal sense” (Haugeland 1985),“The art of creating machines that perform functions that require intelligence when performed by people” (Kurzweil, 1990),“The study of mental faculties through the use of computational models” (Charniak et al. 1985),A field of

4、 study that seeks to explain and emulate intelligent behavior in terms of computational processes” (Schalkol, 1990),Systems that think like humans,Systems that think rationally,Systems that act like humans,Systems that act rationally,Views of AI fall into four categories:,What is AI?,AI,Search engin

5、es,Labor,Appliances,Science,What else?,AI,Honda Humanoid Robot,Walk,Turn,Stairs,Turing test (1936),Alan turing （1912-1954） Computers can fool people, people who believe it is not the machine, then it should be called intelligent.,1956, the American scholar McCarthy who is considered the father of ar

6、tificial intelligence of organized a Society, many experts and scholars gathered together for a discussion of up to two months. Inviting them to participate in the Summer Dartmouth Artificial Intelligence Research Society. Since then, this field is named artificial intelligence,McCarthy麥卡錫,Birth of

7、AI,McCarthy麥卡錫,Minsky 明斯基,Shannon 香農(nóng),Birth of AI,Simon-1975,Newell-1975,More, Samuel, Selfridge, Solomonff 莫爾（Princeton ），塞繆爾（IBM），塞爾夫里奇， 索羅莫夫（MIT）,Birth of AI,In machine learning, in 1957 Rosenblatt (羅森布拉特 )successfully developed Perceptron(感知機(jī)); In theorem proving, in 1958 Wang Hao in the IBM-704

8、machine with a 3-5 minute proved all 220 theorem “Principia Mathematica” in the relevant propositional calculus;In 1965, Robinson made due to the resolution principle(歸結(jié)原理); In pattern recognition(模式識別), 1959 Selfridge(塞爾福里奇) launched a pattern recognition program; 1965 Roberts prepared a distinguis

9、hed building block construction procedures(可分辨積木構(gòu)造程序);,The first 10 years of achievement,In terms of problem solving(問題求解): 1960 Newell(紐厄爾) compiled a universal problem solver (GPS), can solve 11 different types of problems; In expert systems(專家系統(tǒng)): the results of the 1968 Feigenbaum(費(fèi)根鮑姆) develope

10、d DENDRAL expert system and put into use; In the artificial intelligence language(人工智能語言): 1960 McCarthy (McCarthy) developed the artificial intelligence language-LISP language.,The first 10 years of achievement,Secondary Translation - Machine Translation the spirit is willing but the flesh is weakt

11、he vodka is good but the meat is rotten Combinatorial explosion problem (組合爆炸)The fact that a program can find a solution in principle does not means that the program contains any of the mechanisms needed to find it in practice. Perceptron limitations(感知機(jī)局限性) A two-input perceptron cannot be trained

12、 to recognize when its two inputs are different.,Difficulties (the late1960s),Feigenbaum(費(fèi)根鮑姆) presented Knowledge Engineering at the 5th IJCAI(International Joint Conference On Artificial Intelligence，國際人工智能聯(lián)合會(huì)議),Knowledge Engineering (1977),Hopfield Neural Networks (Hopfield, 霍普菲爾德，1982) Back-prop

13、agation algorithm (Rumelhart & McClelland, 魯梅爾哈特，麥克萊倫德 1986)Its the most common neural network,Neural Networks,Computational Intelligence thriving (90s-now),Artificial Neural Network人工神經(jīng)網(wǎng)絡(luò) Genetic Algorithm遺傳算法 Fuzzy Reasoning模糊推理 Ant Colony Algorithm蟻群算法 Particle Swarm Optimization粒子群優(yōu)化 Artificial Immune System人工免疫系統(tǒng),Enthusiasm（狂熱）,Computational Intelligence,國際人工智能聯(lián)合會(huì)議,The History of AI,May 1997, the U.S. IBMs “Deep Blue” supercomputer beat the world chess champion Garry Kasparov(卡斯帕羅夫).,Th