Presentation is loading. Please wait.

Presentation is loading. Please wait.

Knowledge-Based Systems

Similar presentations


Presentation on theme: "Knowledge-Based Systems"— Presentation transcript:

1 Knowledge-Based Systems
Priti Srinivas Sajja Associate Professor Department of Computer Science Sardar Patel University Visit priti sajja.info for detail H Created By Priti Srinivas Sajja

2 Created By Priti Srinivas Sajja
Contact Name: Dr. Priti Srinivas Sajja Communication: Mobile : URL :http://pritisajja.info Academic qualifications : Ph. D in Computer Science Thesis title: Knowledge-Based Systems for Socio- Economic Development Subject area of specialization : Artificial Intelligence Publications : 84 in Books, Book Chapters, Journals and in Proceedings of International and National Conferences Created By Priti Srinivas Sajja

3 Created By Priti Srinivas Sajja
This slideshow is available here Created By Priti Srinivas Sajja

4 Created By Priti Srinivas Sajja
Introduction Natural Intelligence Responds to situations flexibly. Makes sense of ambiguous or erroneous messages. Assigns relative importance to elements of a situation. Finds similarities even though the situations might be different. Draws distinctions between situations even though there may be many similarities between them. Artificial Intelligence According to Rich & Knight (1991) “AI is the study of how to make computers do things, at which, at the moment, people are better”. A machine is regarded as intelligent if it exhibits human characteristics generated through natural intelligence. AI is the study of human thought processes and moving toward problem solving in a symbolic and non-algorithmic way. Created By Priti Srinivas Sajja

5 Created By Priti Srinivas Sajja
Introduction “Artificial Intelligence(AI) is the study of how to make computers do things at which, at the moment, people are better” Elaine Rich, Artificial Intelligence, McGraw Hill Publications, 1986 Created By Priti Srinivas Sajja

6 Constituents of artificial intelligence
Introduction where people are better human thought process characteristics we associate with intelligence knowledge using symbols heuristic methods non-algorithmic AI Constituents of artificial intelligence Extreme solution, either best or worst taking  (infinite) time time Acceptable solution in acceptable time Nature of AI solutions Created By Priti Srinivas Sajja

7 Created By Priti Srinivas Sajja
Introduction Turing test will fail to test for intelligence in two circumstances; A machine may well be intelligent without being able to chat exactly like a human; and; The test fails to capture the general properties of intelligence, such as the ability to solve difficult problems or come up with original insights. If a machine can solve a difficult problem that no person could solve, it would, in principle, fail the test. Can you tell me what is *67344? Why Sir? The Boss could not judge who was replying, thus the machine is as intelligent as the secretary. The Turing test Created By Priti Srinivas Sajja

8 Creating Your Own Test…
Introduction Creating Your Own Test… Can you find any test to check the given system is intelligent or not? Reacts differently Walks, perceives, tests, smells, and feels like human If it talks like human Makes and understands joke Solves your problem Translates, summarizes, and learns conceptually form a test and use it in different situation before accepting it. Created By Priti Srinivas Sajja

9 Created By Priti Srinivas Sajja
Introduction Rich & Knight (1991) classified and described the different areas that Artificial Intelligence techniques have been applied to as follows: Mundane Tasks Perception - vision and speech Natural language understanding, generation, and translation Commonsense reasoning Robot control Expert Tasks Engineering - design, fault finding, manufacturing planning, etc. Scientific analysis Medical diagnosis Financial analysis Formal Tasks Games - chess, backgammon, checkers, etc. Mathematics- geometry, logic, integral calculus, theorem proving, etc. Created By Priti Srinivas Sajja

10 Sophistication and complexity
Data Pyramid Basic transactions by operational staff using data processing Middle management uses reports/info. generated though analysis and acts accordingly Higher management generates knowledge by synthesizing information Strategy makers apply morals, principles, and experience to generate policies Wisdom (experience) Knowledge (synthesis) Information (analysis) Data (processing of raw observations ) Volume Sophistication and complexity TPS DSS, MIS KBS WBS IS Created By Priti Srinivas Sajja

11 Raw Data through fact finding
Data Pyramid Data Information Knowledge Wisdom Understanding Experience Novelty Researching Absorbing Doing Interacting Reflecting Raw Data through fact finding Concepts Rules Heuristics and models Created By Priti Srinivas Sajja

12 Hardware base/technology
Data Pyramid MIS DSS EES ESS ES EIS TPS OAS 1990 1970 1950 Hardware base/technology Users’ requirements IS Intelligent systems: 21st century challenge EES: Executive Expert System is a hybridization of an expert system , executive information system, and decision support system. Software resources Created By Priti Srinivas Sajja

13 Knowledge-Based Systems Created By Priti Srinivas Sajja
KBS Knowledge-Based Systems (KBS) are Productive Artificial Intelligence Tools working in a narrow domain. Created By Priti Srinivas Sajja

14 Created By Priti Srinivas Sajja
Comparison Traditional Computer-Based Information Systems (CBIS) Knowledge-Based Systems (KBS) Gives a guaranteed solution and concentrate on efficiency Adds powers to the solution and concentrates on effectiveness without any guarantee of solution Data and/or information processing approach Knowledge and/or decision processing approach Assists in activities related to decision making and routine transactions; supports need for information Transfer of expertise; takes a decision based on knowledge, explains it, and upgrades it, if required Examples are TPS, MIS, DSS, etc. Examples are expert systems, CASE-based systems, etc. Manipulation method is numeric and algorithmic Manipulation method is primarily symbolic/connectionist and nonalgorithmic These systems do not make mistakes These systems learn by mistakes Need complete information and/or data Partial and uncertain information, data, or knowledge will do Works for complex, integrated, and wide areas in a reactive manner Works for narrow domains in a reactive and proactive manner KBS Created By Priti Srinivas Sajja

15 Created By Priti Srinivas Sajja
Categories of KBS Expert systems Linked systems Intelligent tutoring system CASE based system Intelligent user interface for databases KBS Created By Priti Srinivas Sajja

16 Created By Priti Srinivas Sajja
Provides a high intelligence level Assists people in discovering and developing unknown fields Offers a vast amount of knowledge in different areas Aids in management Solves social problems in better way than the traditional CBIS Acquires new perceptions by simulating unknown situations Offers significant software productivity improvement Significantly reduces cost and time to develop computerized systems Objectives Created By Priti Srinivas Sajja

17 Components of KBS Structure Created By Priti Srinivas Sajja
Knowledge base is a repository of domain knowledge and meta knowledge. Inference engine is a software program, which infers the knowledge available in the knowledge base Enriches the system with self-learning capabilities Structure Knowledge base Inference engine User interface Explanation and reasoning Self- learning Friendly interface to users working in their native language Provides explanation and reasoning facilitates Created By Priti Srinivas Sajja

18 Advantages and Difficulties Created By Priti Srinivas Sajja
Permanent Documentation of Knowledge Cheaper Solution and Easy Availability of Knowledge Dual Advantages of Effectiveness and Efficiency Consistency and Reliability Justification for Better Understanding Self-Learning and Ease of Updates Characteristics Completeness of Knowledge Base Characteristics of Knowledge Large Size of Knowledge Base Acquisition of Knowledge Slow Learning and Execution Development model and Standards Created By Priti Srinivas Sajja

19 Satellite Broadcasting (Internet, TV, and Radio)
Experience Satellite Broadcasting (Internet, TV, and Radio) Printed Media Experts Sources of knowledge Types of Knowledge Tacit knowledge Explicit knowledge Commonsense knowledge Informed commonsense knowledge Heuristic knowledge Domain knowledge Meta knowledge Types of Knowledge Created By Priti Srinivas Sajja

20 Created By Priti Srinivas Sajja
Knowledge Components Facts Facts represent sets of raw observation, alphabets, symbols, or statements. The earth moves around the sun. Every car has a battery. Rules Rules encompass conditions and actions, which are also known as antecedents and consequences. If there is daylight, then the Sun is in the sky. If the car does not start, then check the battery and fuel. Heuristics It is a rule of thumb, which is practically applicable however, does not offer guarantee of solution. If there is total eclipse of the sun, there is no daylight, even though the sun is in the sky. If it is a rainy season and a car was driven through water, silencer would have water in it, so it may not start. Types of Knowledge Created By Priti Srinivas Sajja

21 Typical Inference Cycle
Inference Engine An inference engine is a software program that refers the existing knowledge, manipulates the knowledge according to need, and makes decisions about actions to be taken. Match Select Execute Conflict Setting Knowledge Base Working Memory Typical Inference Cycle Structure Created By Priti Srinivas Sajja

22 Created By Priti Srinivas Sajja
Forward Chaining Consider initial facts and store them into working memory of the knowledge base. Check the antecedent part (left hand side) of the production rules. If all the conditions are matched, fire the rule (execute the right hand side). If there is only one rule do the following: Perform necessary actions. Modify working memory and update facts. Check for new conditions. If more than one rule is selected use the conflict resolution strategy to select the most appropriate rules and go to step 4. Continue until appropriate rule is found and executed. Structure Created By Priti Srinivas Sajja

23 Created By Priti Srinivas Sajja
Backward Chaining Start with possible hypothesis, say H. Store the hypothesis H in working memory along with the available facts. Also consider a rule indicator R, and set it to Null. If H is in the initial facts, the hypothesis it is proven. Go to step 7. If H is not in the initial facts, find a rule, say R, that has a descendent (action) part mentioning the hypothesis. Store R in working memory. Check conditions of the R and match with the existing facts. If matched, then fire the rule R and stop. Otherwise, continue to step 4. Structure Created By Priti Srinivas Sajja

24 Created By Priti Srinivas Sajja
A Short Break …. Created By Priti Srinivas Sajja

25 Other Knowledge Sources
IDENTIFICATION Experts Other Knowledge Sources CONCEPTULIZATION IDENTIFICATION Knowledge Acquisition Techniques Literature review Protocol analysis Diagram-based techniques Concept sorting etc. KBS requirements Knowledge Engineer User Knowledge representation Knowledge discovery and verification IMPLEMENTATION FORMALIZATION Knowledge Base Data Base Cases and documents Automatic creation from cases TESTING Activities in the knowledge acquisition process Knowledge Acquisition Find suitable experts and a knowledge engineer Proper homework and planning Interpreting and understanding the knowledge provided by the experts Representing the knowledge provided by the experts Created By Priti Srinivas Sajja

26 Knowledge Acquisition
Problem Solving Talking and Story Telling Supervisory Style Dealing with multiple experts Knowledge Engineer Hierarchical handling Group handling Individual expert handling Knowledge Acquisition Created By Priti Srinivas Sajja

27 Update by knowledge engineer Update by expert through interface
Knowledge Update Update by knowledge engineer Self-update by system Update by expert through interface Knowledge Acquisition Created By Priti Srinivas Sajja

28 Knowledge Representation
Constant: RAM, LAXMAN Variable: Man Function: Elder (RAM, LAXMAN) returns any value, here, RAM Predicate: Mortal (RAM) returns a Boolean value, here, True WFF: ‘If you do not exercise, you will gain weight is represented as:  x[{Human(x) ^ ~Exercise (x)}  Gain weight(x)] Factual Knowledge Representation Name: Power Bike Broad Category: Land Vehicle Sub Category: Gearless Fuel Type: Gas Cost: $ 350 Capacity: Two persons Speed: Km/Hour Person Doctor Patient Medicine Give Instance Agent Recipient Semantic Network Knowledge Representation Frame Created By Priti Srinivas Sajja

29 Knowledge Representation Created By Priti Srinivas Sajja
Name: Visit to Pharmacy Props: Money Symptoms Treatment Medicine Roles: Dentist - D Receptionist - R Patient - P Entry Conditions: Patient P has toothache. Patient P has money. Exit Conditions Patient P has less money. Patient P returns with treatment. Patient P has appointment. Patient P has prescription. Scene 1: Entry P enters to the pharmacy. P goes to reception. P meets R. P pays registration and/or fees and gets appointment. Go to Scene 2. Scene 2: Consulting Doctor P meets D. P conveys symptoms. P gets treatment. P gets appointment. Go to Scene 3. Scene 3: Exiting P pays money to R. P exits the pharmacy. Knowledge Representation Script Created By Priti Srinivas Sajja

30 Created By Priti Srinivas Sajja
Examples Typology Created By Priti Srinivas Sajja

31 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

32 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

33 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

34 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

35 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

36 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

37 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

38 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

39 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

40 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

41 Created By Priti Srinivas Sajja
Examples Created By Priti Srinivas Sajja

42 Created By Priti Srinivas Sajja
Examples ELIZA is a computer program and an early example of primitive natural language processing. ELIZA was written at MIT by Joseph Weizenbaum between 1964 to 1966. ELIZA was implemented using simple pattern matching techniques, but was taken seriously by several of its users, even after Weizenbaum explained to them how it worked. It was one of the first chatterbots in existence. Examples Created By Priti Srinivas Sajja

43 Created By Priti Srinivas Sajja
Examples // Description: this is a very basic example of a chatterbot program by Gonzales Cenelia #include <iostream> #include <string> #include <ctime> int main() { std::string Response[] = {"I HEARD YOU!", "SO, YOU ARE TALKING TO ME.", CONTINUE, I AM LISTENING.", "VERY INTERESTING CONVERSATION.", "TELL ME MORE..." }; srand((unsigned) time(NULL)); std::string sInput = ""; std::string sResponse = ""; while(1) { std::cout << ">"; std::getline(std::cin, sInput); int nSelection = rand() % 5; sResponse = Response[nSelection]; std::cout << sResponse << std::endl; } return 0; Created By Priti Srinivas Sajja

44 Created By Priti Srinivas Sajja


Download ppt "Knowledge-Based Systems"

Similar presentations


Ads by Google