* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Expert Systems
Survey
Document related concepts
Embodied cognitive science wikipedia , lookup
Wizard of Oz experiment wikipedia , lookup
Intelligence explosion wikipedia , lookup
Ethics of artificial intelligence wikipedia , lookup
Incomplete Nature wikipedia , lookup
Existential risk from artificial general intelligence wikipedia , lookup
Computer Go wikipedia , lookup
Philosophy of artificial intelligence wikipedia , lookup
Ecological interface design wikipedia , lookup
Human–computer interaction wikipedia , lookup
Personal knowledge base wikipedia , lookup
Transcript
Welcome to IS 335 Expert Systems and Decision Support Systems Dr.Khalid A. Eldrandaly,PhD,GISP Professor of IS Dr.Khalid Eldrandaly LECTURE Three Expert Systems Overview Dr.Khalid Eldrandaly What is intelligence ? There is no unique definition of intelligence. Webster's dictionary defines intelligence as, " the ability to understand new or trying situations ". The more commonly accepted definition is " the ability to perceive, understand and learn about new situations ". The human brain is equipped with such an enormous potential to perceive, understand and learn. If this ability can be duplicated in a computer system, the computer should be classified as being intelligence according to the definition of intelligence . As the human intelligence is captured by an external system; hence the name artificial intelligence. 3 AI Concepts and Definitions The origins of AI can be traced back to 1950s. In 1956, at a Dartmouth Conference, John McCarthy coined the term “artificial intelligence (AI).” AI aims to understand human cognitive processes and modeling them on the computer so that the computer can solve the process the same way the human would do. AI can be defined as the field of computer science concerned with designing intelligent computer systems. 4 AI Objectives Make machines smarter Understand what intelligence is Make machines more useful 5 Signs of Intelligence Learn or understand from experience Make sense out of ambiguous or contradictory messages Respond quickly and successfully to new situations Use reasoning to solve problems Dr.Khalid Eldrandaly 6 Turing Test for Intelligence A computer can be considered to be smart only when a human interviewer, “conversing” with both an unseen human being and an unseen computer, can not determine which is which Dr.Khalid Eldrandaly 7 Artificial Intelligence versus Natural Intelligence Dr. Khalid Eldrandaly 8 AI Advantages Over Natural Intelligence More permanent Ease of duplication and dissemination Less expensive Consistent and thorough Can be documented Can execute certain tasks much faster than a human Can perform certain tasks better than many or even most people Dr. Khalid Eldrandaly 9 Natural Intelligence Advantages over AI Natural intelligence is creative People use sensory experience directly Can use a wide context of experience in different situations AI - Very Narrow Focus Dr. Khalid Eldrandaly 10 AI Methods are Valuable Models of how we think Methods to apply our intelligence Can make computers easier to use Can make more knowledge available Simulate parts of the human mind Dr. Khalid Eldrandaly 11 The AI Field Many Different Sciences & Technologies Linguistics Psychology Philosophy Computer Science Electrical Engineering Hardware and Software Etc. Dr. Khalid Eldrandaly 12 Major AI Areas Expert Systems Natural Language Processing Speech Understanding Robotics and Computer Vision Smart Computing Etc. Dr. Khalid Eldrandaly 13 EXPERT SYSTEMS In 1970s AI scientists laid a conceptual breakthrough in AI field, which can be simply stated “ to make a program intelligent, provide it with lots of high-quality , specific knowledge about some problem area.” Expert systems(ES) can be defined as: A sophisticated computer program that manipulate knowledge to solve problems efficiently and effectively in a narrow area. A computer program designed to model the problem-solving ability of a human expert. 14 Expert Systems Attempt to Imitate Expert Reasoning Processes and Knowledge in Solving Specific Problems Most Popular Applied AI Technology Enhance Productivity Augment Work Forces Narrow Problem-Solving Areas or Tasks Dr. Khalid Eldrandaly 15 Expert Systems Provide Direct Application of Expertise Expert Systems Do Not Replace Experts, But They Make their Knowledge and Experience More Widely Available Permit Nonexperts to Work Better Dr. Khalid Eldrandaly 16 Procedural Systems use previously defined procedures use numerical processing use linear processing developed and maintained by programmers structured designed information and control integrated can’t explain its reasoning 17 Expert Systems Use heuristics to solve problems use formal reasoning use parallel and interactive processing developed and maintained by knowledge engineers interactive and cyclic design knowledge and control separated can explain its reasoning 18 Knowledge Engineering Knowledge engineering is the art of bringing the principles and tools of AI research to bear on difficult applications problem requiring experts knowledge for their solutions knowledge engineering is the science of building expert systems 19 Knowledge Engineering Activities Knowledge acquisition : collection of knowledge from the domain expert. Knowledge representation : representing the knowledge collected, in some formal scheme for implementation by computer. 20 Knowledge Engineering Activities Domain Expert Knowledge Engineer Expert System 21 Expert Systems Architecture The term architecture refers to the science and method of design that determine the structure of the expert system. 22 Three Major ES Components Knowledge Base Inference Engine User Interface Dr. Khalid Eldrandaly 23 Three Major ES Components User Interface Inference Engine Knowledge Base Dr. Khalid Eldrandaly 24 All ES Components Knowledge Acquisition Subsystem Knowledge Base Inference Engine User Interface Blackboard (Workplace) Explanation Subsystem (Justifier) Knowledge Refining System User Most ES do not have a Knowledge Refinement Component Dr. Khalid Eldrandaly 25 Knowledge Acquisition Subsystem Knowledge acquisition is the accumulation, transfer and transformation of problemsolving expertise from experts and/or documented knowledge sources to a computer program for constructing or expanding the knowledge base Requires a knowledge engineer Dr. Khalid Eldrandaly 26 Knowledge Base The knowledge base contains the knowledge necessary for understanding, formulating, and solving problems Two Basic Knowledge Base Elements Facts Special heuristics, or rules that direct the use of knowledge Knowledge is the primary raw material of ES Incorporated knowledge representation Dr. Khalid Eldrandaly 27 Inference Engine The brain of the ES The control structure (rule interpreter) Provides methodology for reasoning Dr. Khalid Eldrandaly 28 User Interface Language processor for friendly, problemoriented communication NLP, or menus and graphics Dr. Khalid Eldrandaly 29 Blackboard (Workplace) Area of working memory to Describe the current problem Record Intermediate results Records Intermediate Hypotheses and Decisions 1. Plan 2. Agenda 3. Solution Dr. Khalid Eldrandaly 30 Explanation Subsystem (Justifier) Traces responsibility and explains the ES behavior by interactively answering questions -Why? -How? -What? -(Where? When? Who?) Knowledge Refining System Learning for improving performance Dr. Khalid Eldrandaly 31 The Human Element in Expert Systems Expert Knowledge Engineer User Others Dr. Khalid Eldrandaly 32 The Expert Has the special knowledge, judgment, experience and methods to give advice and solve problems Provides knowledge about task performance Dr. Khalid Eldrandaly 33 The Knowledge Engineer Helps the expert(s) structure the problem area by interpreting and integrating human answers to questions, drawing analogies, posing counterexamples, and bringing to light conceptual difficulties Usually also the System Builder Dr. Khalid Eldrandaly 34 The User Possible Classes of Users A non-expert client seeking direct advice (ES acts as a Consultant or Advisor) A student who wants to learn (Instructor) An ES builder improving or increasing the knowledge base (Partner) An expert (Colleague or Assistant) The Expert and the Knowledge Engineer Should Anticipate Users' Needs and Limitations When Designing ES Dr. Khalid Eldrandaly 35 Other Participants System Builder Systems Analyst Tool Builder Vendors Support Staff Network Expert Dr. Khalid Eldrandaly 36 Expert Systems Building Tools Languages : 1. Conventional languages such as C 2. AI languages such as PROLOG • • Shells such as EXSYS Knowledge Engineering Environments such as VRS 37 Problem Areas Addressed by Expert Systems Interpretation systems Prediction systems Diagnostic systems Design systems Planning systems Monitoring systems Debugging systems Repair systems Instruction systems Control systems Dr. Khalid Eldrandaly 38 Expert Systems Benefits Increased Output and Productivity Decreased Decision Making Time Increased Processes and Product Quality Reduced Downtime Capture Scarce Expertise Flexibility Easier Equipment Operation Elimination of Expensive Equipment Dr. Khalid Eldrandaly 39 Operation in Hazardous Environments Accessibility to Knowledge and Help Desks Integration of Several Experts' Opinions Can Work with Incomplete or Uncertain Information Provide Training Enhancement of Problem Solving and Decision Making Improved Decision Making Processes Improved Decision Quality Ability to Solve Complex Problems Knowledge Transfer to Remote Locations Enhancement of Other MIS Dr. Khalid Eldrandaly 40 Lead to Improved decision making Improved products and customer service Sustainable strategic advantage May enhance organization’s image Dr. Khalid Eldrandaly 41 Problems and Limitations of Expert Systems Knowledge is not always readily available Expertise can be hard to extract from humans Each expert’s approach may be different, yet correct Hard, even for a highly skilled expert, to work under time pressure Expert system users have natural cognitive limits ES work well only in a narrow domain of knowledge Dr. Khalid Eldrandaly 42 Most experts have no independent means to validate their conclusions Experts’ vocabulary often limited and highly technical Knowledge engineers are rare and expensive Lack of trust by end-users Knowledge transfer subject to a host of perceptual and judgmental biases ES may not be able to arrive at valid conclusions ES sometimes produce incorrect recommendations Dr. Khalid Eldrandaly 43 Limitations of Expert Systems Expert Systems are not good at: 1- representing temporal knowledge 2- representing spatial knowledge 3- performing commonsense reasoning 4- handling inconsistent knowledge 5- recognizing the limits of their ability 44 See you next Wednesday inshaa Allah to discuss the following important topic: Knowledge Engineering Good Luck 45