1 artificial intelligence
Download as PPTX, PDF2 likes369 views
The document discusses artificial intelligence and expert systems. It defines AI as creating intelligent machines that can learn, think, perceive, analyze and act like humans. Expert systems are described as computer programs that mimic human experts by applying specialized knowledge and reasoning skills to solve complex problems. Examples of early expert systems like DENDRAL and MYCIN are provided. The roles, uses, and typical structure of expert systems are outlined.
![Formal Definitions for Artificial
Intelligence
Systems that think like humans Systems that act like humans
“The exciting new effort to make
computers think … machines with minds,
in the full and literal sense
“The art of creating machines that
perform functions that require
intelligence when performed by people”
(Kurzweil 1990)
“[The automation of] activities that we
associate with human thinking, activities
such as decision making, problem
solving, learning …” (Bellman, 1978)
“The study of how to make computers do
things at which, at the moment, people
are better” (Rich and Knight, 1991)
“The study of mental faculties through
the use of computational models”
(Charniak and McDermott)
“A field of study that seeks to explain and
emulate intelligent behavior in terms of
computational processes” (Schalkoff,
1990)
“The study of computation that make it
possible to perceive reason and act”
(Winston 1992)
“The branch of computer science that is
concerned with the automation of
intelligent behavior” (Luger and
Stubblefield, 1993)](https://image.slidesharecdn.com/1-artificialintelligence-170730074730/85/1-artificial-intelligence-8-320.jpg)
1 artificial intelligence
- 1. Artificial Intelligence What is Artificial Intelligence?
- 2. What is Intelligence? • The ability of problem solving demonstrates intelligence. • The ability to think, plan and schedule demonstrate intelligence. • Memory and correct and efficient memory and information manipulation also counts towards ones intelligence.
- 3. What is Intelligence? • The ability to tackle ambiguous and fuzzy problems demonstrates intelligence. • The ability to learn and recognize demonstrates intelligence. • The ability to understand and perceive demonstrates intelligence.
- 4. Intelligent Machines • A machine searches through a mesh and finds a path. • A machine solves problems like the next number in the sequence. • A machine develops plans. • A machine diagnoses and prescribes. • A machine answers ambiguous questions.
- 5. Intelligent Machines • A machine recognizes fingerprints. • A machine understands. • A machine perceives. • A machine does MANY MORE SUCH THINGS! • A machine behaves as HUMANS do.
- 6. Intelligent Machines • We will have to call such a machine Intelligent. Is this real or natural intelligence? NO! This is Artificial Intelligence.
- 7. What is Artificial Intelligence? • According to the father of Artificial Intelligence, John McCarthy, it is “The science and engineering of making intelligent machines, especially intelligent computer programs”.
- 8. Formal Definitions for Artificial Intelligence Systems that think like humans Systems that act like humans “The exciting new effort to make computers think … machines with minds, in the full and literal sense “The art of creating machines that perform functions that require intelligence when performed by people” (Kurzweil 1990) “[The automation of] activities that we associate with human thinking, activities such as decision making, problem solving, learning …” (Bellman, 1978) “The study of how to make computers do things at which, at the moment, people are better” (Rich and Knight, 1991) “The study of mental faculties through the use of computational models” (Charniak and McDermott) “A field of study that seeks to explain and emulate intelligent behavior in terms of computational processes” (Schalkoff, 1990) “The study of computation that make it possible to perceive reason and act” (Winston 1992) “The branch of computer science that is concerned with the automation of intelligent behavior” (Luger and Stubblefield, 1993)
- 9. How Humans Think? • Introspection: that is trying to catch out own thoughts as they go by. • Psychological Experiments: that concern with the study of science of mental life.
- 10. To Put In Brief • Artificial Intelligence is an effort to create systems that can learn, think, perceive, analyze and act in the same manner as real humans. • Strong AI: Machines act intelligently and they have real conscious minds • Weak AI: Machines can be made to act as if they are intelligent.
- 11. Philosophy of AI • A question by John McCarthy ‘’Can a machine think and behave like humans do?” • The development of AI started with the intention of creating similar intelligence in machines that we find and regard high in humans.
- 12. Goals of AI • To Create Expert Systems − The systems which exhibit intelligent behavior, learn, demonstrate, explain, and advice its users. • To Implement Human Intelligence in Machines − Creating systems that understand, think, learn, and behave like humans.
- 13. What Contributes to AI? • Artificial intelligence is a science and technology based on disciplines such as Computer Science, Biology, Psychology, Linguistics, Mathematics, and Engineering. A major thrust of AI is in the development of computer functions associated with human intelligence, such as reasoning, learning, and problem solving.
- 14. What Contributes to AI?
- 15. Applications of AI • Gaming -In games where machine can think based on large numbers • Natural Language Processing -where machines understand human natural language spoken by humans • Expert Systems -Provide reasons and advices for users • Vision Systems • Speech Recognition • Handwriting Recognition • Intelligent Robots
- 16. Expert Systems Who are human experts? • They possess specialized knowledge in a certain area • They possess experience in the given area • They can provide, upon elicitation, an explanation of their decisions • They have a skill set that enables them to translate the specialized knowledge gained through experience into solutions.
- 17. What is an expert system? • A computer program designed to model the problem solving ability of a human expert • Expert Systems • Knowledge • Reasoning
- 18. History and Evolution • There was a realization in the late 60’s that the general framework of problem solving was not enough to solve all kinds of problem. • Specialized knowledge is very important of practical systems.
- 19. Some Expert Systems DENDRAL • DENDRAL, an early expert system, developed beginning in 1965 at Stanford University. • A chemical-analysis expert system for NASA to perform chemical analysis of Martian soil for space missions. • To determine molecular structure which was based on “Test & Generate” method.
- 20. MYCIN • MYCIN is the name of a decision support system developed by Stanford University in the early- to mid-seventies. • Built to assist physicians in the diagnosis of infectious diseases as particular blood disease. • The system (also known as an "expert system") would ask a series of questions designed to emulate the thinking of an expert in the field of infectious disease (hence the "expert-"), and from the responses to these questions give a list of possible diagnoses, with probability, as well as recommend treatment (hence the "decision support-").
- 21. Comparison of a human expert system and an expert system
- 22. Roles of an expert system • Replacement of expert: To replace human expert to an expert system where it is feasible in some situations. The solution would be based on safety, location or cost. • Assisting expert: An assisting expert system would aid an expert in a task to increase productivity, managing a complex situation.
- 23. How are expert systems used • Control applications: In control applications, ES are used to adaptiv ely govern/regulate the behavior of a system. • Design: ES are used for design applications to configure objects under given design constraints.
- 24. How are expert systems used • Diagnosis and Prescription: ES can serve to identify system malfunction points. • Instruction and Simulation: ES can be used to model processes or systems for operational study, or for use along with tutoring applications • Interpretation: Producing an understanding of situation from given information. • Planning and prediction: ES may be used for planning applications, e.g. recommending steps for a robot to carry out certain steps, cash management planning.
- 25. How are expert systems used • Appropriate domains for expert systems: When analyzing a particular domain to see if an expert system may be useful, ES ask: 1.Can the problem be effectively solved by conventio nal programming? 2. Is the domain well-bounded? 3. What are the practical issues involved?
- 26. Expert system structure • Focused area of expertise • Specialized Knowledge (Long- term Memory, LTM) • Case facts (Short-term Memory, STM) • Reasons with these to form new knowledge • Solves the given problem