Introduction to Expert Systems {Artificial Intelligence}
Download as PPT, PDF11 likes12,633 views
The document provides an introduction to expert systems. It defines an expert system as a computer system that emulates the decision-making abilities of a human expert. The key components of an expert system are a knowledge base containing the expertise knowledge and an inference engine that draws conclusions from the knowledge base. Expert systems offer advantages like increased availability, reduced costs, reliability, and the ability to explain their reasoning. However, they also have limitations like dealing with uncertainty and an inability to generalize knowledge like humans.
Introduction to Expert Systems {Artificial Intelligence}
- 1. Introduction to Expert Systems Expert Systems: Principles and Programming
- 2. 2 What is an expert system? “An expert system is a computer system that emulates, or acts in all respects, with the decision-making capabilities of a human expert.” • Expert Systems = knowledge-based systems = knowledge-based expert systems
- 3. Expert System • Expert System is one of the sub- areas of AI. An expert system is a set of programs that manipulate knowledge to solve problem in a specialized area • An expert system is more than a database program. A database program retrieve and store the data 3
- 4. 4 What is an expert system? •The basic idea is that if a human expert can specify the steps of reasoning by which a problem may be solved, so too can an expert system. •Restricted domain expert systems (extensive use of specialized knowledge at the level of human expert) function well which is not the case of general-purpose problem solver.
- 5. 5 Expert System Main Components • Knowledge base – obtainable from books, magazines, knowledgeable persons, etc.; or expertise knowledge. Knowledge base of an expert system contains both behavioral and procedural knowledge. • Inference engine – draws conclusions from the knowledge base.
- 6. 6 Basic Functions of Expert Systems
- 7. 7 Problem Domain vs. Knowledge Domain • In general, the first step in solving any problem is defining the problem area or domain to be solved. • An expert’s knowledge is specific to one problem domain – medicine, finance, science, engineering, etc. • The expert’s knowledge about solving specific problems is called the knowledge domain. • The problem domain is always a superset of the knowledge domain. • Expert system reasons from knowledge domain.
- 8. 8 Problem Domain vs. Knowledge Domain • Example: infections diseases diagnostic system does not have (or require) knowledge about other branches such as surgery.
- 9. 9 Problem and Knowledge Domain Relationship
- 10. 10 Advantages of Expert Systems • Increased availability: on suitable computer hardware • Reduced cost • Reduced danger: can be used in suitable environment. • Permanence: last for ever, unlike human who may die, retire, quit. • Multiple expertise: • Increased reliability
- 11. 11 Advantages Continued • Explanation: explain in detail how arrived at conclusions. • Fast response: (e.g. emergency situations). • Steady, unemotional, and complete responses at all times: unlike human who may be inefficient because of stress or fatigue. • Intelligent tutor: provides direct instructions (student may run simple programs and explaining the system’s reasoning). • Intelligent database: access a database intelligently (e.g. data mining).
- 12. Developing An Expert System • Identification • Conceptualization • Formalization • Implementation • Testing 12
- 13. Steps in expert system development 13 • Identification – Determining the characteristics of problem • Conceptualization – Finding concepts to represent the knowledge • Formalization – Designing structure to organize the knowledge • Implementation – Formulation of rules the embody the knowledge • Testing – Validation of rules
- 14. Expert System Building Tools Shells and skeletons • When system can be built without any domain specific knowledge. Such systems are known as skeletons systems, shells or simply AI tools. • A shell often includes tools that help with the design, development and testing of the knowledge base. • With the shell approach expert system representing many different problem domains may be developed and delivered with the same software environment. 14
- 15. Shells (Tools) • Many commercial shells are available today, ranging in size from shells on PCs, to shells on workstations. Its range from hundred to tens of thousand dollars, and range in complexity from simple. • Some of such tools/shells and their applications are given below- 15
- 16. Shell tools • ART(Automated Reasoning tools) • ADS (Aion Development System)- os • Acquire – Step by step methodology used for knowledge base system . • Babylon- is modular configurable (is used to logical programming) • Expert ease – designed for decision support which can run on microcomputer such as IBM PC. 16
- 17. Shell tools • GURU – is used DBMS and RDBMS • HUGIN – is used for probability function • KEE (Knowledge Engineering Environment) – is used for frames and scripts. • KES (Knowledge Engineering System) – Available in different versions to run on machines. • Personal Consultant – Fitted parameters and production rules . 17
- 18. Expert System Architecture • There are many architectures, on which expert systems are built upon. 1.Ruled based system architecture - is used in expert and other types of knowledge based system in the production systems also called as rule base system. 18
- 19. 19 Structure of a Rule-Based Expert System
- 20. Rule based system • Rule bases system is same as the production system. • When we creating and maintain the production system and find initial state to goal state then rule base system is used. • Learning module and history file are not common components of expert systems when they are provided they are used to assist in building and refining the knowledge base. 20
- 21. 2. Non production system architecture • They are classified into six categories – 1.Associative or semantics architecture 2.Frame and rule structures 3.Decision network 4.Black board system architecture 5.Neural networks 6.Analogical reasoning 21
- 22. Associative or semantics architecture • Associative network representations are especially useful in hierarchical representation of knowledge structures for example Binary tree. • Associative network representations are not a popular form of representation for standard expert systems. • They are used in natural languages or computer version systems. 22
- 23. Continue • One expert system based on the use of associative network representation is CASNET (Casual Associative Network), which was developed at Rutgers for glaucoma one of the leading causes of blindness. Main components of this network are – 1. patient observation 2. Disease categories 23
- 24. Frames and rule structures • Frame is network of nodes and relations. • Expert system has been constructed with frame architecture and numbers of building tools that create and manipulate frame structured system have been developed. • Example- A frame based system is PIP (present illness program) system developed at 1970’s. 24
- 25. Continued - • This medical knowledge in PIP is organized in frame structures where each frames is composed of categories of slot with names such as typical findings. • Disease, solution, research, doctors, patients etc. 25
- 26. 2. Decision Architecture • Decision architecture is similar to decision tree in decision tree we can find initial state(Starting node) and goal state(Last node). 26
- 27. Black Board Architecture • Black board architecture is special types of knowledge base system. Its differ from forward and backward chaining in production systems the point may be chosen in any way of the given path and searching the tree. • Black board system have been gaining popularity recently. They have been applied to a number of application areas. 27
- 28. • One of the first application was HEARSAY family of projects, which are speech – understanding systems. 28
- 29. Neural Network Architecture • Neural networks are large networks. Neural network is used to solve large problem into short form. It is used to solve mathematically and statistical problem. ∑ xi i= 1 to 10 29
- 30. Analogical Reasoning • In analogical reasoning is used to match current problem, and if matched then solution can be generated with the previous experience. With some modification such system uses past experience based on promise that human beings use analogical reasoning experimental reasoning to learn and solve complex problems. 30
- 31. 31 Limitations of Expert Systems • Uncertainty = having limited knowledge (more than possible outcomes) • Both human experts and expert systems must be able to deal with uncertainty. • Limitation 1: most expert systems deals with shallow knowledge than with deep knowledge. • Shallow knowledge – based on empirical and heuristic knowledge. • Deep knowledge – based on basic structure, function, and behavior of objects.
- 32. 32 Limitations of Expert Systems • Limitation 2: typical expert systems cannot generalize through analogy to reason about new situations in the way people can. • Solution 1 for limitation 2: repeating the cycle of interviewing the expert. • Limitation raised form Solution 1: A knowledge acquisition bottleneck results from the time- consuming and labor intensive task of building an expert system.
- 33. 33 Early Expert Systems • DENDRAL – used in chemical mass spectroscopy to identify chemical constituents • MYCIN – medical diagnosis of illness • DIPMETER – geological data analysis for oil • PROSPECTOR – geological data analysis for minerals • XCON/R1 – configuring computer systems
- 34. 34 Broad Classes of Expert Systems