Artificial Intelligence


Published on

Published in: Education, Technology
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Artificial Intelligence

  1. 1. Chapter 1: An introduction to Artificial Intelligence What exactly is Artificial Intelligence? Artificial Intelligence is the study of how to make computer do things which, at the moment, people do better. This definition is of course somewhat ephemeral because of its reference to the current state of computer science. And it fails to include some areas of potentially very large impact, namely problems that cannot now be solved well by either computer or people. But it provides a good outline of what constitutes artificial Intelligence, and it avoids the philosophical issues that dominate attempts to define the meaning of either artificial or intelligence. Artificial Intelligence is the area of engineering focusing on creating machines that can engage on behaviours that human considers intelligence. The ability to create intelligent machines has intrigued humans since ancient time and today with the advent of computer and 50 years of research into AI programing techniques, the dream of smart machines is becoming reality. Researchers are creating systems which can mimic human thoughts, understand speech, beat the best human chess player, and countless other feats never before possible. The military is applying AI logic to its hi- tech systems, and in the near future Artificial Intelligence may impact our lives. John McCarthy, who coined the term „Artificial Intelligence‟ in 1956, at Massachusetts Institute of Technology, defines it as "the science and John McCarthy engineering of making intelligent machines” Artificial intelligence can be said a crossbreeding of a lot of fields: Philosophy Logic, methods of reasoning, mind as physical system, foundations of learning, language, rationality. Mathematics Formal representation and proof, algorithms, computation, (un)decidability, (in)tractability Statistics Modeling uncertainty, learning from data Economics Utility, decision theory, rational economic agents Neuroscience Neurons as information processing unit 1
  2. 2. Psychology How do people behave, perceive, process cognitive information, represent knowledge Computer Building fast computers Engineering Control Theory Design systems that maximize an objective function over time Linguistics Knowledge representation, grammars Artificial Intelligence is a broad topic, consisting of different field from machine vision to expert system. Artificial Intelligence In order to classify machines as “thinking”, it is necessary to define intelligence. To what degree intelligence consists of, for example, solving complex problems, or making generalization and relationship? And what about perception and comprehension? Researches into the areas of learning of language, and of sensory perception have aided scientist in building intelligent machines. One of the most challenging approaches experts facing is building systems that mimic the behavior of human brain, made up of billions of neurons, and arguably the most complex matter in the universe. Perhaps the best way to gauze the intelligence is British computer scientist Alan Turing‟s test. He stated that a computer would deserve to be called intelligent if it could deceive a human into believing that it was a human. 2
  3. 3. A computer would need the followings to pass Turing test:  Natural language processing: to communicate with examiner.  Knowledge representation: to store and retrieve information provided before or during interrogation.  Automated reasoning: to use the stored information to answer questions and to draw Alan Turing new conclusions.  Machine learning: to adapt to new circumstances and to detect and extrapolate patterns.  Vision (for Total Turing test): to recognize the examiner‟s actions and various objects presented by the examiner.  Motor control (total test): to act upon objects as requested.  Other senses (total test): such as audition, smell, touch, etc. Artificial intelligence has come a long way from its early roots, driven by dedicated researchers. The beginning of AI reaches back before electronics, to philosophers and mathematicians such as Boole and other theorizing on principles that were used as the foundation of AI logic. AI really began to intrigue researchers with the invention of computer in 1943. The technology was finally available, or so it seemed, to simulate George Boole intelligent behavior. Over the next five decades, despite many stumbling blocks, AI has grown from a dozen researchers to thousands of engineers and specialists; and from programs capable of playing checkers, to system designed to diagnose disease. 3
  4. 4. Chapter 2: The history of Artificial Intelligence Evidence of Artificial Intelligence folklore can be traced back to ancient Egypt, but with the development of electronic computer in 1941, the technology finally become available to create machine intelligence. The term Artificial intelligence was first coined in 1956, at Dartmouth conference, and since then Artificial Intelligence has expanded because of the theories and principles developed by its dedicated researchers. From its birth 4 decades ago, there have been a variety of AI programs, and they have impacted other technological developments. Here the brief history of AI is given: 1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turing's "Computing Machinery and Intelligence" 1956 Dartmouth meeting: "Artificial Intelligence" adopted 1950s Early AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1965 Robinson's complete algorithm for logical reasoning 1966-73 AI discovers computational complexity, neural network research almost disappears 1969-79 Early development of knowledge-based systems 1980 AI becomes an industry 1986 Neural networks return to popularity 1987 AI becomes a science 1995 The emergence of intelligent agents Pre-history of AI:  Through history, people thought of mythic “artificial” robots  golden robots of Hephaestus and Pygmalion's Galatea  alchemical means of placing mind into matter  More specific, tangible advances  5th century B.C.  Aristotle invented syllogistic logic, the first formal deductive reasoning system. 4
  5. 5.  13th century.  Talking heads were said to have been created (Roger Bacon and Albert the Great).  Ramon Lull, Spanish theologian, invented machines for discovering nonmathematical truths through combinatory.  15th century  Invention of printing using moveable type. Gutenberg Bible printed (1456).  15th-16th century  Clocks, the first modern measuring machines, were first produced using lathes.  16th century  Clockmakers extended their craft to creating mechanical animals and other novelties.  17th century - The revolution of thinking about thinking  Descartes proposed that bodies of animals are nothing more than complex machines (strong AI).  Variations and elaborations of Cartesian mechanism.  Hobbes published The Leviathan, containing a material and combinatorial theory of thinking.  Pascal created the first mechanical digital calculating machine (1642).  Leibniz improved Pascal's machine to do multiplication & division (1673) and envisioned a universal calculus of reasoning by which arguments could be decided mechanically.  18th century – Mechanical toys Vaucanson‟s Duck Von Kempelen‟s phony mechanical chess player  19th century – Frankenstein‟s birth  George Boole developed a binary algebra representing (some) "laws of thought," published in The Laws of Thought. 5
  6. 6.  Charles Babbage and Ada Byron (Lady Lovelace) worked on programmable mechanical calculating machines.  Mary Shelley published the story of Frankenstein's monster (1818).  Crossing the century bridge  Behaviorism was expounded by psychologist Edward Lee Thorndike in "Animal Intelligence." Pre-birth of AI:  Beginning of the 20th century  Russell and Whitehead published Principia Mathematica.  Capek's play “Rossum's Universal Robots” produced in 1921 (London opening, 1923). First use of the word 'robot' in English.  McCulloch and Pitts publish "A Logical Calculus of the Ideas Immanent in Nervous Activity" (1943), laying foundations for neural networks.  Rosenblueth, Wiener and Bigelow coin the term cybernetics (1943).  Bush published As We May Think (1945) a prescient vision of the future in which computers assist humans in many activities. The era of computer: In 1941 an invention revolutionized every aspect of the storage and processing of information. That invention developed both in U.S. and Germany was the electronic computer. The 1949 innovation, the stored program computer, made the job of entering a program easier, and the advancements in computer theory lead to computer science, and eventually artificial intelligence. With the invention of an electronic means of processing data, came a medium that made AI possible. The beginning of AI: Although the computer provided the technology necessary for AI, it was not until early 1950‟s that the link between human intelligence and machines was Norbert Wiener really observed. Norbert Wiener was one of the first Americans to make observation on the principle of feedback theory. What so important about his research into feedback loops was that Wiener theorized that all intelligent behavior was the result of feedback mechanism. 6
  7. 7. In late 1955, Newell and Simon developed „The logic Theorist‟, considered by many to the first AI program. The program representing each problem as a tree model, would attempt to solve it by selecting the branch that would most likely result in the correct conclusion. The impact that „the logic theorist‟ made on both the public and the field of AI has made it a crucial stepping stone in developing the AI field. In 1956, John McCarthy, regarded as the father of AI organized a conference to draw the talent and expertise of others interested in machine intelligence for a month of brain storming. He invited them to Vermont for “The Dartmouth Summer Research Project on Artificial Intelligence”. Although not a huge success, the Dartmouth conference brought together the founders in AI, and served to lay the groundwork for the future if AI research. Knowledge expansion: Research was placed upon creating system that could efficiently solve problem, by limiting the search, such as the logic theorist and second, making systems that could learn themselves. In 1957, the first version of a new program-„The General Problem Solver‟ was tested. The program developed by same pair which developed „The Logic Theorist‟. The GPS was an extension of Wiener‟s feedback principle, and was capable of solving a greater extent of common sense problems. While more program ware being produced, McCarthy was busy developing a major breakthrough in AI history. In 1958 McCarthy announced his new development; the LISP language, which is still used today. LISP stands for „list processing‟, and was soon adopted as the language of choice among most AI developers. 7
  8. 8. Chapter 3: Branches of AI An AI machine should have and show some intelligent behaviours:  Learn from experience  Apply knowledge acquired from experience  Handle complex situations  Solve problems when important information is missing  Determine what is important  React quickly and correctly to a new situation  Understand visual images  Process and manipulate symbols  Be creative and imaginative  Use heuristics Depending upon these behaviors AI can be classified as following:  Perceptive system  A system that approximates the way a human sees, hears, and feels objects  Vision system  Capture, store, and manipulate visual images and pictures  Robotics  Mechanical and computer devices that perform tedious tasks with high precision  Expert system  Stores knowledge and makes inferences  Learning system  Computer changes how it functions or reacts to situations based on feedback  Natural language processing  Computers understand and react to statements and commands made in a “natural” language, such as English 8
  9. 9.  Neural network  Computer system that can act like or simulate the functioning of the human brain Depending upon the above classification it is realized that AI can have several branches regarding different job. The following is detailed classification with brief description.  Logical AI What a program knows about the world in general the facts of specific situation in which it must act, and its goals are all represented by sentences of some mathematical, logical language. The program decides what to do by inferring that certain actions are appropriate for achieving its goals.  Search AI programs often examine large number of possibilities, e.g. moves in chess game of inferences by a theorem proving program. Discoveries are continuously made about how to do this more efficiently in various domains.  Pattern recognition When a program makes observation of some kind, it is often programmed to compare what it sees with a pattern. For example, a vision program may try to match a pattern of eyes and a nose in a scene in order to find a face. More complex pattern e.g. in a natural language test, in a chess position, or in the history of some event are also studied. These more complex patterns require quite different methods than do the simple patterns that have been studied the most.  Representation Facts about the world have to be represented in some way. Usually languages of mathematical logic are used.  Inference Mathematical, logical deduction is adequate for some purposes, but new methods of non-monotonic inference have been added to logic since 1970s. The simplest kind of non-monotonic reasoning is default reasoning in which a conclusion is to be inferred by default, but the conclusion can be withdrawn if there is evidence to the contrary. For example when we hear of a bird, we may infer that it can fly. But this conclusion can be reversed when we hear that it is a Penguin. It is the 9
  10. 10. possibility that a conclusion may have to be withdrawn that constitutes the non-monotonic character of the reasoning. Ordinary logical reasoning is monotonic in that the set of conclusions that can be drawn from a set of premises is a monotonic increasing function of the premises. Circumscription is another form of non-monotonic reasoning.  Common sense knowledge and reasoning This is the area in which AI is farthest from human level, in spite of the fact that it has been an active research area since the 1950s. while there has been considerable progress, e.g. in developing systems of non- monotonic reasoning and other theories of action, yet more new ideas are needed.  Learning from experience The approaches to AI based on connectionism and neural nets specialize in that. There is also learning of laws expressed in logic. Programs can only learn what facts or behaviors their formalism can represent, and unfortunately learning systems are almost all based on very limited abilities to represent information.  Planning Planning programs start with general facts about the world, especially facts about the effects of actions, facts about the particular situation and a statement of a goal. From these they generate a strategy for achieving the goal. In the most common cases, the strategy is just a sequence of actions.  Epistemology This is a study of the kinds of knowledge that are required for solving problem in the world.  Ontology This is the study of kinds of things that exist. In AI, the program and sentences deal with various kinds of objects, and we study what these kinds are and what their basic properties are. Emphasis on Ontology begins in the 1990s.  Heuristic A heuristic is a way of trying to discover something or an idea imbedded in a program. Heuristic predicates that compare two nodes in a search tree to see if one is better than the other, i.e. constitutes an advance towards the goal, may be more useful. 10
  11. 11. Chapter 4: Approaches: methods used to create intelligence In the quest to create intelligent machines, the field of artificial intelligence has been split into several different approaches based on the opinions about the most promising methods and theories. These rivaling theories have lead researchers in one of two basic approaches: bottom-up and top-down. Bottom-up theorist believe the best way to achieve artificial intelligence is to build electronic replicas of the human brain‟s complex network of neurons, while the top down approach attempts to mimic the brain‟s behavior with computer programs. Neural network and parallel computation The human brain is made up of a web of billions of cells called neurons, and understanding its complexity is seen as one of the last frontiers in scientific research. It is the aim of AI researchers who prefer this bottom-up approach to construct electronic circuits that act as neurons do in the human brain. Although much of the working of the brain remains unknown, the complex network of neurons is what gives human intelligent characteristics. By itself, a neuron is not intelligent, but when grouped together, neuron are able to pass electrical signal through networks. Warren McCulloch, after completing medical school at Yale, along with Walter Pitts, a mathematician proposed a hypothesis to explain the fundamentals of how neural network made the brain work. Based on experiments with neurons, McCulloch and Pitts Warren McCulloch showed that neurons might be Walter Pitts considered devices for processing binary numbers. An important back of mathematic logic, binary numbers, represented as 1‟s & 0‟s or true & false, were also the basis of electronic computer. This link is the basis of compute simulated neural network, also known as Parallel computing. A century earlier the true/false nature of binary numbers is theorized, in 1854 by George Boole in his postulates concerning the laws of thought. Boole‟s principle made up what is known as Boolean algebra, the collection of logic concerning AND, OR, NOT operands. For example according to the laws of thought the statement :( for example all apples are red) 11
  12. 12.  Apples are red --------------- True  Apples are red AND oranges are purple --------------- False  Apples are red OR oranges are purple --------------- True  Apples are red AND oranges are NOT purple -------- True Boole also assumed that the human mind works according to these laws, it performs logical operation that could be reasoned. Ninety years latter Claude Shannon applied Boole’s principles in circuits, the blueprint for electronic computers. Top-down approaches: Expert systems Because of the large storage capacity of computers, Claude Shannon expert systems had the potential to interpret statistics, in order to formulate the rules. An expert system works much like a detective solves a mystery. Using the information, and logic or rules, an expert system can solve the problem. For example if the expert system was designed to distinguish birds it may have the following: YES NO Large? NO YES NO YES Fly? Fly? NO Penguin YES Multi- NO Ostrich YES Crest? coloured? YES Parrot Bald? NO Vulture YES Large Eagle beak? NO Crow YES Red? NO Top-down approach logic Robin Charts like the previous one, represents the logic of expert systems. Using a similar set of rules, experts can have a variety of applications. With improved interfacing, computers may begin to find a larger place in society. 12
  13. 13. Game playing AI based game playing programs combine intelligence with entertainment. On game with strong AI ties is chess. The greatest advances have occurred in the field of games playing. The best computer chess programs are now capable of beating humans. In May, 1997, an IBM super-computer called Deep Blue defeated world chess champion Gary Kasparov in a chess match. These chess playing program can see ahead twenty plus moves in advance each move they make. In addition, the programs have an ability to get progress ably better over time because of the ability to learn from experience. Chess program do not play chess as human plays. In three minutes Deep Thought (a master program) considers 126 million, while human chess master on average consider less than two moves. Herbart Simon suggested that, human chess masters are familiar with favorable board positions, and the relationship with thousands of pieces in small areas. Computers on the other hand, do not take hunches into account. The next move comes from exclusive searches from all moves, and the consequences of the moves based in prion learning. Chess program running on Cray supercomputer have attained a rating of 2600(senior master), in the range of Gary Kasparov, the Russian world champion. TOPIO. A robot, can play table Deep Blue tennis 13
  14. 14. Chapter 5: Application of AI What can we do with AI We have been studying this issue of AI application for quite some time now and know all the terms and facts. But what we all really need to know is what we can do to get our hands on some AI today. How can we as individuals use our own technology? We hope to discuss in depth but as firefly as possible, so that you the consumer can use AI as it is intended. First we should be prepared for a change. Our conservative ways stand in the way of progress.AI is a new step that is very helpful to the society. Machines can do jobs that require detailed instruction followed and mental alertness. AI with its learning capabilities can accomplish those tasks but only if the world‟s conservatives are ready to change and allow this be possibilities. It makes us think about us how early man finally accepted the wheel as a good invention, not something taking away from its heritage or tradition. Secondly, we must be prepared to learn about the capabilities of AI. The more use we get out of the machines the less work is required by us, in turn less injury and stress to human beings. Human beings are a species that learn by trying and we must be prepared to give AI a chance seeing AI as a blessing, not an inhibition. Finally we need to be prepared for the worst of AI. There is always the fear that if AI is learning based; will machines learn that being rich and successful is a good thing, then wage war against economic powers and famous people? There is so many things that can go wrong with a new system, so we must be as prepared as we can be for this new technology. However even though the fear of machines is there, their capabilities are infinite. Whatever we teach AI, they will suggest in the future if a possible outcome arrives from it. AI are like children that need to be taught to be kind, well mannered, and intelligent. If they are to make important decisions, they should be wise. We as citizen need to make sure AI programmers are keeping things on the level. We should be sure they are doing the job correctly, so that no future accident occurs. AIAI teaching computers computer Does this sound a little redundant? Or may be a little redundant? Well just sit back and let me explain. The Artificial Intelligence Application Institute has many projects that they are working on to make their computer learn how to 14
  15. 15. operate themselves with less human input. To have more functionality with less input is an operation for AI technology. I will discuss just two of these projects: „AUSDA‟ and „EGRESS‟. AUSDA is a program which examines software to see if it is capable of handling the task you need performed. If it is not able or is not reliable, AUSDA will instruct you on finding alternative software which would better suit your needs. According to AIAI the software would provide solutions to problems like “identifying the root causes of incidents in which the use of computer software is involved, studying different software development approaches and identifying aspects of these which are relevant to those root causes producing guidelines for using and improving the development approaches studied, and proving support in the integration of these approaches, so that they can be better used for the development and maintenance of safety critical software”. Sure for the computer buffs this program is definitely good news. But what about average person who thinks the mouse is just the computer foot paddle? Where do they fit into computer technology? Well don‟t worry guys, because we nerds are looking out for you too! Just ask AIAI what they have for you, and it turns up the EGRESS is right down your alley. This is a program which is studying human reactions to accidents. It is trying to make a model of how people‟s reaction in panic moment saves lives. Although it seems like in tough situation human would fall apart and have no idea what to do, it is in fact the opposite. Quick decisions are usually made and are effective but not flawless. These computer models will help rescuers make smart decision in time of need. AI can‟t be positive all the time but suggest actions which we can act out and therefore lead to safe rescues. So AIAI is teaching computers do better computers and better people. AI technology will never replace man but can be an extension of our body which allows us to make more rational decision faster. And with institute like AIAI- we continue each step to step forward into progress. No worms in these apples Apple Computer may not have ever been considered as the state of art in Artificial Intelligence, but a second look should be given. Not only are todays PC‟s becoming more powerful but AI influence is showing up in them. From Macros to Voice Recognition technology, PC‟s are becoming our talking buddies. Who else would go surfing with you on short notice-even if it is the net? Who else would care to tell you that you have a business appointment scheduled at 8:35 & 28 seconds and would notify you about it every minute till you told it to shut up. 15
  16. 16. All power Macintoshes come with voice recognition. That‟s right – you tell the computer to do what you want without it having to learn your voice. This implication of AI in personal computer is still very crude but it does work given the correct conditions to work in and a clear voice. Not to mention the requirement of at least 16MBs of RAM for quick use. Also Apple‟s Newton and other hand held notepad have script recognition. Cursive or paint can be recognized by these notepad sized devices. With the Pen that accompanies your silicon notepad you can write a little note to yourself which magically changes into computer text if desired. No more complaining about sloppy written reports if your compute can read your handwriting. If it can‟t read it through- perhaps in the future, you can correct it by dictating your letters instead. Macros provide a huge stress relief as your computer does what you could do more tediously. Macros are old but they are to an extent, intelligent. You have taught the computer to something by doing it only once. In business many times applications are upgraded. But the files must be converted. All of the business records need to be changed into the new software‟s type. Macros save the work of conversion of hundreds of files by a human by teaching the computer to mimic the action of the programmer. Thus teaching the computer a task that it can repeat whenever ordered to do so. The scope of Expert System As stated in the „approaches‟ section, an expert system is able to do the work of a professional. Moreover a computer can be trained quickly, has virtually no operating cost, never forgets what it learns, never calls in sick, retires or goes on vacation. Beyond those, intelligent computers can consider a large amount of information that may not be considered by humans. But to what extent should these systems replace human experts? Or, should they at all? For example some people once considered an intelligent computer as a possible substitute for human control over nuclear weapons, citing that a computer could respond more quickly to a threat. And many AI developers were afraid of the possibilities of program like ELIZA, the psychiatrist and the bond that humans were making with the computer. We can‟t however overlook the benefits of having a computer expert. Forecasting the weather, for example, relies on many variables, and a computer expert can more accurately pool all of its knowledge. Still a computer can‟t rely on the hunches of a human expert, which are sometimes necessary in predicting an outcome.Expert systems have the power and range to aid the benefit, and in some case replace humans, and computer experts, if used with discretion, will benefit human kind. 16
  17. 17. Chapter 6: AI programs ELIZA: An earlier AI program that simulated the behavior of a Rogerian therapist. ELIZA’s knowledge about English and Psychology was coded in a set of simple rule based on Complex and Approximate Matching, Conflict Reasoning. Joseph Weizenbaum’s result of trying to make a program converse in English amazed people when it appeared in 1960’s. the program was able to converse about any subject, because of its stored subject information in data banks. Another feature of ELIZA was its ability to pick up speech patterns. In DOCTOR mode, ELIZA might respond to "My head hurts" with "Why do you say your head hurts?" The response to "My mother hates me" would be "Who else in your family hates you?" ELIZA was implemented using simple pattern matching techniques. A typical conversation is the following: Girl: Men are all alike. Eliza: IN WHAT WAY? Girl: They're always bugging us about something or other. Eliza: CAN YOU THINK OF A SPECIFIC EXAMPLE? Girl: Well, my boyfriend made me come here. Eliza: YOUR BOYFRIEND MADE YOU COME HERE Girl: He says I'm depressed much of the time. Eliza: I AM SORRY TO HEAR YOU ARE DEPRESSED Girl: It's true. I am unhappy Eliza: DO YOU THINK COMING HERE WILL HELP YOU NOT TO BE UNHAPPY Girl: I need some help, that much seems certain. Eliza: WHAT WOULD IT MEAN TO YOU IF YOU GOT SOME HELP Girl: Perhaps I could learn to get along with my mother. Eliza: TELL ME MORE ABOUT YOUR FAMILY Girl: My mother takes care of me. Eliza: WHO ELSE IN YOUR FAMILY TAKES CARE OF YOU Girl: My father. Eliza: YOUR FATHER Girl: You are like my father in some ways. Eliza: WHAT RESEMBLANCE DO YOU SEE Girl: You are not very aggressive but I think you don't want me to notice that. Eliza: WHAT MAKES YOU THINK I AM NOT VERY AGGRESSIVE Girl: You don't argue with me. 17
  18. 18. Eliza: WHY DO YOU THINK I DON'T ARGUE WITH YOU Girl: You are afraid of me. Eliza: DOES IT PLEASE YOU TO BELIEVE I AM AFRAID OF YOU Girl: My father is afraid of everybody. Eliza: WHAT ELSE COMES TO YOUR MIND WHEN YOU THINK OF YOUR FATHER Girl: Bullies. Eliza: DOES THAT HAVE ANYTHING TO DO WITH THE FACT THAT YOUR BOYFRIEND MADE YOU COME HERE As impressive as ELIZA‟s look, Wiezenbaum noted that it understood no more of the girl‟s problem as an alarm clock understands when to go off. For example, the last sentence gives the impression of comprehension, but in fact the program is written so that at one point, it modifies the first sentence and applies it as a response. The General Problem Solver(GPS): General Problem Solver (GPS) was a computer program created in 1957 by Herbert Simon, J.C. Shaw, and Allen Newell intended to work as a universal problem solver machine. Any formalized symbolic problem can be solved, in principle, by GPS. For instance: theorems proof, geometric problems and chess playing. It was based on Simon and Newell's theoretical work on logic machines. While GPS solved simple problems such as the Towers of Hanoi that could be sufficiently formalized, it could not solve any real-world problems because search was easily lost in the combinatorial explosion of intermediate states. The user defined objects and operations that could be done on the objects and GPS generated heuristics by Means-ends analysis in order to solve problems. SAM: Sam is a program from Yale's AI lab which is able to read between the lines, and assume certain facts. The Story: John went to New York by bus. On the bus he talked to an old lady. When he left the bus, he thanked the driver. He took the subway to Leone's. On the subway his pocket was picked. He got off the train and entered Leone's. He had some lasagna. When the check came, he discovered he couldn't pay. The management told him he would have to wash dishes. When he left, he caught a bus to New Haven. 18
  19. 19. Sam's comprehension: (Sam's answers are in italic.) Why did John go to New York? Because John wanted to go to Leone's How did John get to Leone's? John took a bus to New York and then he took the subway to Leone's. Did anything unusual happen on the bus? I don't remember anything Did anything unusual happen on the subway? A thief picked John's pocket. What did John order? John ordered lasagna. Did anything unusual happen at the restaurant? John discovered that he could not pay the check and so he had to wash dishes. Why couldn't John pay the check? Because John didn't have any money. Why didn't John have any money? Because a thief picked John's pocket. How did John get back to New Haven? John went from Leone's by subway and then he went to New Haven by bus. How was John able to take the bus to New Haven? Probably he had a ticket. Sam's logic is represented in frames. For this story Sam might use a restaurant frame, and a subway and bus frame. These frames spell out what events in order most likely would occur in situations. Sam is impressive, because it can draw conclusions from the story that are not specifically stated. Also, with the last response, Sam shows that he can make conjectures without information from the story, with the use of frames. SHRDLU: It was an early natural language understanding computer program, developed by Terry Winograd at MIT from 1968-1970. It was written in the Micro Planner and Lisp programming language on the DEC PDP-6 computer and a DEC graphics terminal. Later additions were made at the computer graphics labs at the University of Utah, adding a full 3D rendering of SHRDLU's "world". The name SHRDLU was derived from ETAOIN SHRDLU, the arrangement of the alpha keys on a Linotype machine, arranged in descending order of usage frequency in English. 19
  20. 20. SHRDLU and block worlds 1. Pick up a red block OK 2. find a block which is taller than the one you are holding and put it into the box. By "it," i assume that you mean the block which is taller than the one i am holding. OK. 3. what does the box contain? The blue pyramid and the blue box 4. what is the pyramid supported by? the box 5. how many blocks are not in the box? four of them 6. is at least one of them narrowed than the one which I told you to pick up? yes, the red cube 7. is it supported? yes, by the table 8. can the table hold blocks? no 9. the blue pyramid is mine I understand 10. I own all blocks which are not red, but I don‟t own anything that supports a pyramid I understand 11. do I own the box? no 12. do I own anything in the box? Yes, two things: the blue box and the blue pyramid 13. will you please stack up both of the red blocks and either a green cube or a pyramid? OK 14. is there a large block behind a pyramid? yes, three of them: a large red one, a large green cube and the blue one. 15. put a small one into the green cube which supports a pyramid OK 16. put the littlest pyramid on top of it OK 20
  21. 21. 17. had you touched any pyramid before you put the green one on the little cube? Yes, the green one 18. when did you pick it up? while i was stacking up the red cube, a large red block and a large green cube 19. why? to get rid of it 20. why did you do that? to clear off the red cube 21. why did you clear off that cube? to put it on a large green cube 22. why did you do that? to stack the red cube, a large block, and a large green cube 23. why did you do that? because you asked me to With SHRDLU's comprehension and logic, AI reached a new level. The name SHRDLU was actually borrowed from MAD magazine, and is made up of, as its author Terry Wingrad explained, the seventh through twelfth frequently used letters in the English language. CYRUS: It is a MOP(memory organization packets) based program which contains episodes taken from the life of a particular individual. It can answer questions that require significant amounts of memory reconstruction. IPP: This program accepts stories about terrorist attack and stores them in an episodic memory. MOPTRANS: This program uses a MOP based memory to understand sentences in one language and translates into another. PROSPECTOR: This is a program that provides advices on mineral exploration. DESIGN ADVISOR: It is a system that critiques chip design. It gives advice to the chip designer who decides to accept or reject the advice. NEUROGAMMON: This program is based on neural network that learns from experience. This is one of the few game playing programs which relies heavily on automatic learning. 21
  22. 22. State of the Artificial Intelligence  Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997  Proved a mathematical conjecture (Robbins conjecture) unsolved for decades  No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego)  During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people  NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft  Proverb solves crossword puzzles better than most humans 22
  23. 23. BIBLIOGRAPHY  “ARTIFICIAL INTRLLIGENCE” by Elaine Rich & Kevin Knight     23