Ce diaporama a bien été signalé.
Le téléchargement de votre SlideShare est en cours. ×

Artificial intelligence introduction

Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Chargement dans…3
×

Consultez-les par la suite

1 sur 28 Publicité
Publicité

Plus De Contenu Connexe

Diaporamas pour vous (20)

Similaire à Artificial intelligence introduction (20)

Publicité

Plus récents (20)

Artificial intelligence introduction

  1. 1. Artificial Intelligence Chapter 1
  2. 2. Objective of the course The main objectives of this course are: • To provide basic knowledge of Artificial Intelligence • To familiarize students with different search techniques • To acquaint students with the fields related to AI and the applications of AI
  3. 3. Details of Syllabus 1. Introduction (4 hrs) 1.1. Definition of Artificial Intelligence 1.2. Importance of Artificial Intelligence 1.3. AI and related fields 1.4. Brief history of Artificial Intelligence 1.5. Applications of Artificial Intelligence 1.6. Definition and importance of Knowledge, and learning. 2. Problem solving (6 hrs) 2.1. Defining problems as a state space search 2.2. Problem formulation 2.3. Problem types, Well‐ defined problems, Constraint satisfaction problem, 2.4. Game playing, Production systems.
  4. 4. Details of Syllabus 3. Search techniques (5 hrs) 3.1. Uninformed search techniques‐ depth first search, breadth first search, depth limit search, and search strategy comparison, 3.2. Informed search techniques‐hill climbing, best first search, greedy search, A* search Adversarial search techniques‐minimax procedure, alpha beta procedure 4. Knowledge representation, inference and reasoning (8 hrs) 4.1. Formal logic‐connectives, truth tables, syntax, semantics, tautology, validity, well‐ formed‐formula 4.2. Propositional logic, predicate logic, FOPL, interpretation, quantification, horn clauses 4.3. Rules of inference, unification, resolution refutation system (RRS), answer extraction from RRS, rule based deduction system
  5. 5. Details of Syllabus 5. Structured knowledge representation (4 hrs) 5.1. Representations and Mappings 5.2. Approaches to Knowledge Representation 5.3. Issues in Knowledge Representation 5.4. Semantic nets, frames 5.5. Conceptual dependencies and scripts 6. Machine learning (6 hrs) 6.1. Concepts of learning, 6.2. Learning by analogy, Inductive learning, Explanation based learning 6.3. Neural networks, 6.4. Genetic algorithm 6.5. Boltzmann Machines
  6. 6. Details of Syllabus 7. Applications of AI (14 hrs) 7.1 Neural networks 7.1.1. Network structure 7.1.2. Adaline network 7.1.3. Perceptron 7.1.4. Multilayer Perceptron, Back Propagation 7.1.5. Hopfield network 7.1.6. Kohonen network 7.2 Expert System 7.2.1. Architecture of an expert system 7.2.2. Knowledge acquisition, induction 7.2.3. Knowledge representation, Declarative knowledge, 7.2.4. Development of expert systems 7.3 Natural Language Processing and Machine Vision 7.3.1. Levels of analysis: Phonetic, Syntactic, Semantic, Pragmatic 7.3.2. Introduction to Machine Vision
  7. 7. Practical: Laboratory exercises should be conducted in either LISP or PROLOG. Laboratory exercises must cover the fundamental search techniques, simple question answering, inference and reasoning. References: 1. E. Rich and Knight, Artificial Intelligence, McGraw Hill, 2009. 2. D. W. Patterson, Artificial Intelligence and Expert Systems, Prentice Hall, 2010. 3. P. H. Winston, Artificial Intelligence, Addison Wesley, 2008. 4. Stuart Russel and Peter Norvig, Artificial Intelligence A Modern Approach, Pearson, 2010 Details of Syllabus Unit Hour Marks Distribution* 1 4 7 2 4 7 3 5 9 4 8 14 5 4 7 6 6 10 7 14 26 Total 45 80
  8. 8. Evaluation Criteria • Assessment 1- 4 • Assessment 2- 8 • Attendance - 4 • Homework -2 • Class Performance -2
  9. 9. Intelligence  Computational part of the ability to achieve goals.  involving higher mental process. Example: pattern recognition, solving problems, classification, learning, creativity, deduction, making analogies, languages recognition, and knowledge and many more. Two major “consensus” definitions of intelligence: From Mainstream Science on Intelligence (1994) A very general mental capability that, among other things, involves the ability to reason, Plan, solve problems, think abstractly, comprehend complex ideas, learn quickly and learn from experience. It is not merely book learning, a narrow academic skill, or test- taking smarts. Rather, it reflects a broader and deeper capability for comprehending our surroundings- making sense” of things, or “figuring out” what to do.
  10. 10. Intelligence From Intelligence: Knowns and Unknowns (1995) Individuals differ from one another in their ability to understand complex ideas, to adapt Effectively to the environment, to learn from experience, to engage in various forms of reasoning, [and] to overcome obstacles by taking thought. Although these individual differences can be substantial, they are never entirely consistent: a given person’s intellectual performance will vary on different occasions, in different domains, as judged by different criteria. Concepts of “intelligence” are attempts to clarify and organize this complex set of phenomena.
  11. 11. Intelligence 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  Intelligent behaviors Everyday tasks: communicate with others, recognize a friend, recognize who is calling, translate from one language to another, interpret a photograph, talk, and cook a dinner. Formal tasks: prove a logic theorem, geometry, calculus, play chess. Expert tasks: engineering design, medical designers, financial analysis, knowledge applying successfully in new situation, reason to solve problem and discover hidden knowledge.
  12. 12. Introduction to AI • Definitions of artificial intelligence vary along two main dimensions. • The ones are concerned with thought processes and reasoning, whereas the ones address behavior. • The definitions also measure success in terms of human performance, whereas the other ones measure against an ideal concept of intelligence, which we will call rationality.
  13. 13. Systems that think like humans Systems that think rationally “The exciting new effort to make computers think…..machine with minds, in the full and literal sense.”(Haugeland, 1985) “[The automaton of] activities that we associate with human thinking, activities such as decision-making, problem solving, learning…..” (Bellman, 1978) “The study of mental faculties through the use of computational models.” (Charniak and McDermott, 1985) “The study of the computations that make it possible to perceive, reason, and act.” (Winston, 1992) Systems that act like humans Systems that act rationally “The art of creating machines that perform functions that require intelligence when performed by people.” (Kurzweil, 1990) “The study of how to make computer do things at which, at the moment, people are better.” (Rich and Knight, 1991) “A field of study that seeks to explain and emulate intelligent behavior in terms of computational processes.”(Schalkoff., 1990) “The branch of computer science that is concerned with the automation of intelligent behavior” (Luger and Stubblefield ,1993) AI Approaches
  14. 14. Acting humanly: The Turing Test Approach • The Turing Test, proposed by Alan Turing (1950), was designed to provide a satisfactory 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. • Consider the following setting. There are two rooms, A and B. One of the rooms contains a computer. The other contains a human. The interrogator is outside and does not know which one is a computer. He can ask questions through a teletype and receives answers from both A and B. The interrogator needs to identify whether A or B are humans. • To pass the Turing test, the machine has to fool the interrogator into believing that it is human.
  15. 15. Acting humanly: The Turing Test Approach • The computer must behave intelligently. To achieve human-level performance in all cognitive tasks the computer would need to possess the following capabilities: • Natural language processing: to enable it to communicate successfully in English (or some other human language); • Knowledge representation to store information provided before or during the interrogation effectively & efficiently; • Automated reasoning to retrieve & answer questions using the stored information and to draw new conclusions; • Machine learning to adapt to new circumstances and to detect and extrapolate patterns. Total Turing Test includes a video signal so that the interrogator can test the subject's perceptual abilities. To pass the total Turing Test, the computer will need • Computer vision: computer vision to perceive objects, and • Robotics: robotics to move them about.
  16. 16. Thinking humanly: The cognitive modelling approach • If we are going to say that a given program thinks like a human, we must have some way of determining how humans think. We need to get inside the actual workings of human minds. There are two ways to do this: • Through introspection: catch our thoughts while they go by • Through psychological experiments: • Cognitive science tries to model human mind based on experimentation. • Cognitive modeling approach tries to act intelligently while actually internally doing something similar to human mind. • Cognitive science brings together computer models from AI and experimental techniques from psychology to try to construct precise and testable theories of the workings of the human mind.
  17. 17. Thinking rationally: The laws of thought approach • Humans are not always rational. Rational can be defined in terms of logic. Logic represents facts about the world. Logic can’t express everything e.g. uncertainty knowledge or informal knowledge. For example I think you are very intelligent person. • It is the study of mental facilities through the use of computational models; that it is, the study of the computations that make it possible to perceive, reason, and act. This approach firmly grounded in logic i.e., how can knowledge be represented logically, and how can a system draw deductions? • There are two main obstacles to this approach. First, it is not easy to take informal knowledge and state it in the formal terms required by logical notation, particularly when the knowledge is less than hundred percent certain. Second, there is a big difference between being able to solve a problem "in principle" and doing so in practice. • For example: Ram is a man. All men are mortal. The conclusion is : Ram is mortal
  18. 18. Acting rationally: The rational agent approach • Rational behavior is doing the right thing which is expected to maximize goal achievement, given the available information. Acting rationally means acting so as to achieve one's goals, given one's beliefs. An agent is just something that perceives and acts. The correct inferences is often part of being a rational agent because one way to act rationally is to reason logically and then act on ones conclusions. The study of AI as rational agent design has two advantages: • It is more general than the logical approach because correct inference is only a useful mechanism for achieving rationality, not a necessary one. • It is more amenable to scientific development than approaches based on human behavior or human thought because a standard of rationality can be defined independent of humans.
  19. 19. Importance of AI • Speed of AI implementation • Potential impact on society • Priority of AI by every Large Tech company • Shortage of knowledge worker • To gain competitive advantages. • Logical Implication worldwide. • Ethical Development • Communication of Advantages and Opportunities • Collaboration between Private and Public Sector
  20. 20. The Foundation of Artificial Intelligence • Philosophy (428 B.C.-present) • Mathematics (B.C. 800-present) • Economics (1776-present) • Neuroscience (1861-present) • Psychology (1879-present) • Computer Engineering (1940-present) • Control Theory (1948-present) • Linguistics (1957-present)
  21. 21. Artificial Intelligence Application Areas • Game Playing • Much of the early research in state space search was done using common board games such as checkers, chess, and the 15-puzzle. • Games can generate extremely large search spaces. These are large and complex enough to require powerful techniques for determining what alternative to explore • Automated reasoning and Theorem Proving • Theorem-proving research was responsible in formalizing search algorithms and developing formal representation languages such as predicate calculus and the logic programming language • Knowledge-Based Systems • Data mining, expert systems, knowledge management, KBS methodology, ontologies • Expert knowledge is a combination of a theoretical understanding of the problem and a collection of heuristic problem-solving rules
  22. 22. Artificial Intelligence Application Areas • Natural Language Understanding and Semantics One of the long-standing goals of AI is the creation of programming that are capable of understanding and generating human language • Natural Language Understanding • Speech Understanding • Language Generation • Machine Translation • Information retrieval and text mining • Modelling Human Performance • Capture the human mind (knowledge representation)
  23. 23. Artificial Intelligence Application Areas • Motion and manipulation • A robot perform a sequence of actions without responding to changes and correct errors could hardly considered intelligent • It should have some degree of sensors and algorithms to guild it • Robotics to handle such tasks as object manipulation and navigation, with sub- problems of localization (knowing where you are), mapping (learning what is around you) and motion planning (figuring out how to get there) • Machine Learning and Perception • Detecting credit card fraud, stock market analysis, classifying DNA sequences, • speech and handwriting recognition, object and facial recognition in computer vision. • Alternative representations • Artificial Neural Networks : Mathematical / computational model that tries to simulate the structure and/or functional aspects of biological neural • Genetic Algorithm • Social and business intelligence • Social and customer behavior modelling
  24. 24. Artificial Intelligence Application Areas • Medicine • Image guided surgery • Image analysis and enhancement • Text Processing • Web pages, e-mails • Articles in the news • Automated language translation • Information retrieval • Text classification and organization • Document summarization • Planning and Workflow Systems • Modelling, task setting, planning, execution, monitoring and coordination of activities
  25. 25. Knowledge and Learning • Knowledge is a theoretical or practical understanding of a subject that helps us to solve problems in particular domain, to predict what will happen next and to explain why and how something has happened. • Knowledge is “the sum of what is known: the body of truth, information, and principles acquired by mankind.” Or, "Knowledge is what I know, Information is what we know." • There are many other definitions such as: • Knowledge is "information combined with experience, context, interpretation, and reflection. It is a high-value form of information that is ready to apply to decisions and actions." (T. Davenport et al., 1998)
  26. 26. Knowledge and Learning • Knowledge is “human expertise stored in a person’s mind, gained through experience, and interaction with the person’s environment." (Sunasee and Sewery, 2002) • Knowledge is “information evaluated and organized by the human mind so that it can be used purposefully, e.g., conclusions or explanations." (Rousa, 2002) • Knowledge consists of information that has been: • Interpreted, • Categorized, • Applied, experienced and revised
  27. 27. Knowledge and Learning • In general, knowledge is more than just data, it consist of: facts, ideas, beliefs, heuristics, associations, rules, abstractions, relationships, customs. Research literature classifies knowledge as follows: • Classification-based Knowledge » Ability to classify information • Decision-oriented Knowledge » Choosing the best option • Descriptive knowledge» State of some world (heuristic) • Procedural knowledge » How to do something • Reasoning knowledge » What conclusion is valid in what situation? • Assimilative knowledge » What its impact is?
  28. 28. Knowledge and Learning • Key issues confronting the designer of AI system are: • Knowledge acquisition: Gathering the knowledge from the problem domain • Knowledge representation: Expressing the identified knowledge into some knowledge representation language such as propositional logic, predicate logic etc. • Knowledge manipulation: Large volume of knowledge has no meaning until up to it is processed to deduce the hidden aspects of it. Knowledge is manipulated to draw conclusions from knowledgebase. • Learning • It is concerned with design and development of algorithms that allow computers to evolve behaviors based on empirical data such as from sensor data. • A major focus of learning is to automatically learn to recognize complex patterns and make intelligent decision based on data. • A complete program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.

×