1 Course Outline (Types of XPS ) o Rule-based expert systems o Conflict resolution o Uncertainty management o Fuzzy expert systems o Evolutionary computation (Genetic algorithms) o Neural expert systems o Neuro-fuzzy systems Hybrid systems o Fuzzy evolutionary systems o Knowledge engineering 2 Socrates o Athens—Greece year 460 BC; a young man contemplating wedlock, asks Socrates for his advice. The wise one replies: “By all means, marry, if you get a good wife, you'll become happy; if you get a bad one, you'll become a philosopher”.
3 Expert System o year 2011; a young man asks “Socrates” the same question. The wise one replies: “Based on income compatibility, age, employment status, marriage penalty tax liability and cohabitating couple economy; you have a low chance of a successful marriage. Well “Socrates” is not communicating via a paranormal medium—it is an “Expert System”.
4 Early KBS Success Stories o DENDRAL • identification of chemical constituents o MYCIN • diagnosis of illnesses o PROSPECTOR • analysis of geological data for minerals • discovered a mineral deposit worth $100 million o XCON/R1 • configuration of DEC VAX computer systems • saved lots of time and millions of dollars 5 Success Stories: Deep Blue o Year 1997, Deep Blue defeats chess grandmaster Gary Kasparov and this year Watson defeats jeopardy champions. o Deep Blue demonstrated solving extremely complex but logically well bounded problems like chess. Watson on the other hand solved the problem of meaning behind natural languages, which inherently is unbounded. Both Deep Blue and Watson are indicative of the great strides made in the field of Artificial Intelligence.
6 Success Stories o In December 2013, a small group of AI researchers from a company called DeepMind, released a ground-breaking paper called “PlayingAtari with Deep Reinforcement Learning”. A little over a month later, Google announced that they had bought DeepMind for a really big sum of money.
o In January of 2016, Google announced that the
appropriately named AlphaGo was able to beat the reigning Go champion of the world.
7 Expert Systems o AI-complete fields like natural language processing and open domain Question Answering are still in the realm of computer science research. It may take a while for such fields to become useful for mainstream commercial applications. o One AI discipline that has matured and found applicability in diverse domains like internal medicine, accounting, finance, organic chemistry etc. is Expert Systems. 8 AI Applications
9 What is an Expert System? o An expert system is a computer system that emulates, or acts in all respects, with the decision-making capabilities of a human expert. o An expert system is functionally equivalent to a human expert in a specific problem domain of reasonable complexity. Why do we need to create an Expert System if a human expert can solve it? o Low cost of expertise o Response without cognitive bias o 24/7 availability with high reliability o Clone the expert o Use in hazardous environments o Ability to explain the reasoning without attitude. Definitions “Expert System” o A computer system that emulates the decision-making ability of a human expert in a restricted domain [Giarratano & Riley 1998] o Edward Feigenbaum • “An intelligent computer program that uses knowledge and inference procedures to solve problems that are difficult enough to require significant human expertise for their solutions.” o The term Knowledge-Based System (KBS) is often used synonymously 12 What is an Knowledge-Based System (KBS)? o relies on internally represented knowledge to perform tasks o utilizes reasoning methods to derive appropriate new knowledge o usually restricted to a specific problem domain o some systems try to capture common-sense knowledge
13 Main Components of a KBS User
Expertise Knowledge Base
Facts / Information User Interface
Inference Engine Expertise Developer
14 Main ES Components o Knowledge base • contains essential information about the problem domain • often represented as facts and rules o Inference engine • mechanism to derive new knowledge from the knowledge base and the information provided by the user • often based on the use of rules o User interface • interaction with end users • development and maintenance of the knowledge base 15 General Concepts of ES o Knowledge acquisition • transfer of knowledge from humans to computers • sometimes knowledge can be acquired directly from the environment (machine learning) o Knowledge representation • suitable for storing and processing knowledge in computers o Inference • mechanism that allows the generation of new conclusions from existing knowledge in a computer o Explanation • illustrates to the user how and why a particular solution was generated 16 Rules and Humans o rules can be used to formulate a theory of human information processing • rules are stored in long-term memory • temporary knowledge is kept in short-term memory • sensory input or thinking triggers the activation of rules • activated rules may trigger further activation • a cognitive processor combines evidence from currently active rules o this model is the basis for the design of many rule-based systems • also called production systems 18 Related Developments o Semantic Web • extension of the World Wide Web • includes knowledge representation and reasoning capabilities o Decision Support Systems • less emphasis on autonomy o Data Mining • extraction of knowledge from large quantities of data o Sensemaking • computer support for quicker, easier understanding of complex domains or situations
22 Rule-Based ES o knowledge is encoded as IF … THEN rules • these rules can also be written as production rules
o the inference engine determines which rule antecedents are satisfied
• the left-hand side must “match” a fact in the working memory
o satisfied rules are placed on the agenda
o rules on the agenda can be activated (“fired”)
• an activated rule may generate new facts through its right-hand side • the activation of one rule may subsequently cause the activation of other rules
23 Example Rules IF … THEN Rules Rule: Red_Light antecedent LHS IF the light is red (Left-Hand-Side) THEN stop Rule: Green_Light IF the light is green consequent RHS THEN go (Right-Hand-Side)
Production Rules antecedent (LHS)
the light is red => stop consequent (RHS) the light is green => go MYCIN Sample Rule Human-Readable Format IF the stain of the organism is gram negative AND the morphology of the organism is rod AND the aerobiocity of the organism is gram anaerobic THEN the there is strongly suggestive evidence (0.8) that the class of the organism is enterobacteriaceae MYCIN Format IF (AND (SAME CNTEXT GRAM GRAMNEG) (SAME CNTEXT MORPH ROD) (SAME CNTEXT AIR AEROBIC) THEN (CONCLUDE CNTEXT CLASS ENTEROBACTERIACEAE TALLY .8) 25 KBS Elements o knowledge base o inference engine o working memory o agenda o explanation facility o knowledge acquisition facility o user interface
26 KBS Structure Details
Knowledge Base Knowledge Acquisition User Interface
Facility
Inference Engine Agenda
Explanation Facility Working Memory
27 Forward and Backward Chaining (methods of rule activation) o Forward chaining (data-driven) • reasoning from facts to the conclusion • as soon as facts are available, they are used to match antecedents of rules • a rule can be activated if all parts of the antecedent are satisfied • often used for real-time expert systems in monitoring and control • examples: CLIPS, OPS5 o Backward chaining (query-driven) • starting from a hypothesis (query), supporting rules and facts are sought until all parts of the antecedent of the hypothesis are satisfied • often used in diagnostic and consultation systems • examples: EMYCIN
28 CLIPS introduction Writing “Hello world” in CLIPS knowledge as Rules o A rule captures a set of actions to perform in response to certain stimuli. The stimuli come from the information in the working memory of an expert system. o A rule consists of two parts : • Left hand side (LHS) or antecedent • Right hand side (RHS) or consequent 32
