Every great story on the planet happened when someone decided not to give up, but kept going no matter what.
--Your friends at LectureNotes

Note for Artificial Intelligence - AI by Prakash Poudel

  • Artificial Intelligence - AI
  • Note
  • Tribhuwan university - TU
  • Computer Science Engineering
  • B.Tech
  • 1 Offline Downloads
  • Uploaded 9 months ago
0 User(s)
Download PDFOrder Printed Copy

Share it with your friends

Leave your Comments

Text from page-1

Introduction to Artificial Intelligence Unit_1 What is intelligence? There is no agreed definition or model of intelligence. Einstein said, "The true sign of intelligence is not knowledge but imagination." Socrates said, "I know that I am intelligent, because I know that I know nothing." In Rich Dad, Poor Dad, Robert Kiyosaki, says, “Intelligence is the ability to make finer distinctions.” Many dictionary says that intelligence is, “the ability for logic, understanding, self-awareness, learning, emotional knowledge, reasoning, planning, creativity, and problem solving. I define intelligence as a biopsychological potential to process specific forms of information in certain kinds of ways. Thus, intelligence is:  the ability to reason  the ability to understand  the ability to create  the ability to Learn from experience  the ability to plan and execute complex tasks What is artificial Intelligence? Artificial intelligence, sometimes abbreviated AI, is a branch of computer science that focuses on enabling computers to take on human characteristics, perform people tasks, and think human thoughts. The term was first used by a Stanford researcher, John McCarthy, in the mid-1950s (1956). Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think. AI is accomplished by studying how human brain thinks and how humans learn, decide, and work while trying to solve a problem, and then using the outcomes of this study as a basis of developing intelligent software and systems. According to the father of Artificial Intelligence, John McCarthy, it is “The science and engineering of making intelligent machines, especially intelligent computer programs”. Intelligence in machines is called artificial intelligence, which is commonly implemented in computer systems using programs and, sometimes, appropriate hardware. Different definitions of AI are given by different books/writers. These definitions can be divided into two dimensions. Top dimension is concerned with thought processes and reasoning, whereas bottom dimension addresses the behavior. The definition on the left measures the success in terms of fidelity of human performance, whereas definitions on the right measure an ideal concept of intelligence, which is called rationality. Er. Prakash Poudel Jigyasu Page 1

Text from page-2

Introduction to Artificial Intelligence Unit_1 Thinking humanly: The cognitive modeling approach    Thinking humanly means trying to understand and model how the human mind works. The field of Cognitive Science focuses on modeling how people think There are (at least) two possible routes that humans use to find the answer to a question: – We reason about it to find the answer. This is called “introspection”. – We conduct experiments to find the answer, drawing upon scientific techniques to conduct controlled experiments and measure change. Thinking rationally: The laws of thought approach      Trying to understand how we actually think is one route to AI but another approach is to model how we should think. The “thinking rationally” approach to AI uses symbolic logic to capture the laws of rational thought as symbols that can be manipulated. Reasoning involves manipulating the symbols according to well-defined rules, kind of like algebra The result is an idealized model of human reasoning. This approach is attractive to theorists For example, “Socrates is a man; all men are mortal; therefore Socrates is mortal.” These laws of thought were supposed to govern the operation of the mind, and initiated the field of logic. Acting humanly: The Turing Test approach    This is a problem that has greatly troubled AI researchers for years. They ask the question “when can we count a machine as being intelligent?” The Turing Test, proposed by Alan Turing (1950), was designed to provide a satisfactory TURING TEST operational definition of intelligence. Turing defined intelligent behavior as the ability to achieve human-level performance in all cognitive tasks, sufficient to fool an interrogator. Roughly speaking, the test he proposed is that the computer should be interrogated by a human via a teletype, and passes the test if the interrogator cannot tell if there is a computer or a human at the other end. In order to pass the Turing Test, a program that succeeded would need to be capable of  Natural Language Processing: to enable it to communicate successfully in English( or some other human language)  Knowledge representation: to store information before or during the interrogation  Automated Reasoning: to use the stored information to answer the question and to draw the new conclusions  Machine learning: to detect new circumstances and to detect and extrapolate patterns Turing’s test deliberately avoided direct physical interaction between the interrogator and the computer, because physical simulation of a person is unnecessary for intelligence. However, the socalled total Turing Test includes a video signal so that the interrogator can test the TOTAL TURING TEST subject’s perceptual abilities, as well as the opportunity for the interrogator to pass physical objects “through the hatch.” To pass the total Turing Test, the computer will need; computer vision to perceive objects, and robotics to move them about. Er. Prakash Poudel Jigyasu Page 2

Text from page-3

Introduction to Artificial Intelligence Unit_1 Acting rationally: The rational agent approach  Rational behavior: doing the right thing  The right thing: that which is expected to maximize goal achievement, given the available information  Acting rationally means acting to achieve one’s goals, given one’s beliefs or understanding about the world.  An intelligent agent is one that acts rationally with respect to its goals. For example, an agent that is designed to play a game should make moves that increase its chances of winning the game.  In this approach, AI is viewed as the study and construction of rational agents. Q. What do you mean by Turing Test? Explain. The Turing test developed by Alan Turing(Computer scientist) in 1950. He proposed that “Turing test is used to determine whether or not computer (machine) can think intelligently like human” or not. The Turing test is used to measure a machine's ability to think and is an important concept in the philosophy of artificial intelligence. Imagine a game of three players having two humans and one computer, an interrogator (as human) is isolated from other two players. The interrogator job is to try and figure out which one is human and which one is computer by asking questions from both of them. To make the things harder computer is trying to make the interrogator guess wrongly. In other words computer would try to indistinguishable from human as much as possible. The “standard interpretation” of the Turing Test, in which the interrogator is given the task of trying to determine which player, is a computer and which is a human. The interrogator is limited to using the responses to written questions to make the determination. If interrogator wouldn’t be able to distinguish the answers provided by both human and computer then the computer passes the test and machine (computer) is considered as intelligent as human. In other words, a computer would be considered intelligent if its conversation couldn’t be easily distinguished from a human’s. “Turing Test is a poor test of intelligence that it encourages trickery, not intelligent behavior, and that many intelligent systems would fail this test.” Er. Prakash Poudel Jigyasu Page 3

Text from page-4

Introduction to Artificial Intelligence Unit_1 A brief History of AI The modern history of AI begins with the development of stored-program electronic computers. Here is the short history of AI during 20th century –  1956: John McCarthy coined the term Artificial Intelligence. Demonstration of the first running AI program at Carnegie Mellon University.  1957-1965:  The General Problem Solver (GPS) demonstrated by Newell, Shaw & Simon.  John McCarthy invents LISP programming language for AI.  computers can understand natural language well enough  1966-1972:  Progress was slower than expected, Increase in knowledge representation research  a robot, equipped with motion, perception  A problem solving technique was developed. MYCIN to diagnose blood infections was developed  First Expert system developed  Prolog language Released  1973-1985:  A Robot capable of using vision to locate and assemble models was developed.  The first computer-controlled autonomous vehicle was built.  Japanese fifth generation computer project  Electric Dreams is released, a film about a love triangle between a man, a woman and a personal computer.  1985-2000:  The autonomous drawing program, Aaron, created by Harold Cohen.  Major advances in all areas of AI such as; Case-based reasoning, Multi-agent planning, Scheduling, Data mining etc.  The Deep Blue Chess Program beats the world chess champion, Garry Kasparov.  2000-Present:  MIT displays Kismet, a robot with a face that expresses emotions, Interactive robot pets ("smart toys") become commercially available  Google DeepMind's AlphaGo defeats Go champion Lee Sedol, Speech Recognition, voice recognition, face recognition, iris recognition, handwriting recognition, several autonomous robots etc. Applications of AI AI has been dominant in various fields such as – 1. Gaming − AI plays crucial role in strategic games such as chess, poker, tic-tac-toe, etc., where machine can think of large number of possible positions based on heuristic knowledge. 2. Natural Language Processing − It is possible to interact with the computer that understands natural language spoken by humans. 3. Expert Systems − There are some applications which integrate machine, software, and special information to impart reasoning and advising. Machine can be expert but cannot be intelligent than human. One of the first expert systems was MYCIN in 1974, which diagnosed bacterial Er. Prakash Poudel Jigyasu Page 4

Lecture Notes