Presentation is loading. Please wait.

Presentation is loading. Please wait.

Artificial Intelligence

Similar presentations


Presentation on theme: "Artificial Intelligence"— Presentation transcript:

1 Artificial Intelligence
Priti Srinivas Sajja Professor Department of Computer Science Sardar Patel University Visit pritisajja.info for details H Created by Priti Srinivas Sajja

2 Created by Priti Srinivas Sajja
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 Rural Development (2000) Subject area of specialization : Artificial Intelligence Publications : 118 in Books, Book Chapters, Journals and in Proceedings of International and National Conferences Created by Priti Srinivas Sajja

3 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. Created by Priti Srinivas Sajja

4 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

5 AI Artificial intelligence Introduction human thought process
where people are better human thought process characteristics we associate with intelligence knowledge using symbols heuristic methods non-algorithmic AI Constituents of artificial intelligence Created by Priti Srinivas Sajja

6 Created by Priti Srinivas Sajja
Introduction 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
Testing Intelligence 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. AI Tests 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 conceptually form a test and use it in different situation
Can you find any test to check the given system is intelligent or not? Walks, perceives, tests, smells, and feels like human AI Tests Makes and understands joke Reacts differently Solves your problem If it talks like human 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
Rich & Knight (1991) classified and described the different areas that Artificial Intelligence techniques have been applied to as follows: Applications 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
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 Data pyramid Data Pyramid Created by Priti Srinivas Sajja

11 General structure of KBS
According to the classifications by Tuthhill & Levy (1991), five main types of KBS exists: Expert systems Linked Systems CASE based Systems Intelligent Tutoring Systems Intelligent User Interface for Database Knowledge base Inference engine User interface Explanation and reasoning Self- learning General structure of KBS Knowledge-Based Systems (KBS) are Productive Artificial Intelligence Tools working in a narrow domain. Knowledge Based Systems Created by Priti Srinivas Sajja

12 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 Knowledge Based Systems Created by Priti Srinivas Sajja

13 Hierarchical handling Individual expert handling
Problem Solving Talking and Story Telling Supervisory Style Dealing with Multiple Experts Knowledge Acquisition Knowledge Engineer Hierarchical handling Group handling Individual expert handling Created by Priti Srinivas Sajja

14 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 Knowledge Based Systems Data Base Cases and documents Automatic creation from cases TESTING Activities in the knowledge acquisition process 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

15 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 Knowledge Based Systems 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 Frame Created by Priti Srinivas Sajja

16 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 Based Systems Script Created by Priti Srinivas Sajja

17 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 Based Systems Created by Priti Srinivas Sajja

18 Created by Priti Srinivas Sajja
domains disease, indication=symbol patient=string predicates hypothesis(patient, disease) symptom(patient, indication) response(char) go clauses go:- write("What is the patient's name?"), nl, readln(Patient), hypothesis(Patient, Disease), write(Patient," probably has ",Disease,"."), nl. go:-write("Sorry, I don't seen to be able to "), nl, write("diagnose the disease."), nl. Example Created by Priti Srinivas Sajja

19 Created by Priti Srinivas Sajja
symptom(Patient, fever):- write("Does ",Patient," have a fever (y/n)?"), response(Reply), Reply='y'. symptom(Patient, rash):- write("Dose ",Patient," have a rash (y/n)?"), symptom(Patient, headache):- write("Dose ",Patient," have a headache (y/n)?"), symptom(Patient, runny_nose):- write("Dose ",Patient," have a runny nose (y/n)?"), response(Reply), Reply='y'. symptom(Patient, conjunctivities):- write("Dose ",Patient," have conjunctivities (y/n)?"), symptom(Patient, cough):- write("Dose ",Patient," have a cough (y/n)?"), /*… you may write number of symptoms here …..*/ Example Created by Priti Srinivas Sajja

20 Created by Priti Srinivas Sajja
hypothesis(Patient,measles):- symptom(Patient,fever), symptom(Patient,cough), symptom(Patient,conjunctivities), symptom(Patient,runny_nose), symptom(Patient,rash). hypothesis(Patient, german_measles):- symptom(Patient,headache), hypothesis(Patient, flu):- symptom(Patient,body_ache), symptom(Patient,chills), symptom(Patient,sore_throat), symptom(Patient,runny_nose).  /* number of hypothesis you may include here….*/  response(Reply):- readchar(Reply), write(Reply), nl. Example Created by Priti Srinivas Sajja

21 Created by Priti Srinivas Sajja
OUTPUT IN DIALOG BOX: Goal: go What is the Patient’s Name? Bond Does Bond Have a fever (y/n)? y Does Bond Have a cough (y/n)? y Does Bond Have conjunctivities (y/n)? y Does Bond Have a rash (y/n)? y Does Bond Have a runny nose (y/n)? y Bond probably has measles. Example Created by Priti Srinivas Sajja

22 Created by Priti Srinivas Sajja
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. Example Created by Priti Srinivas Sajja

23 Created by Priti Srinivas Sajja
// 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; Example Created by Priti Srinivas Sajja

24 Created by Priti Srinivas Sajja

25 Created by Priti Srinivas Sajja

26 Created by Priti Srinivas Sajja

27 Created by Priti Srinivas Sajja
Intelligence, explanation and reasoning Partial self learning, uncertainty handling Documentation of knowledge Proactive problem solving Cost effectiveness Nature of knowledge Large volume of knowledge Knowledge acquisition techniques Little support to engineer AI based systems Shelf life of knowledge and system Development Effort Pros and Cons Created by Priti Srinivas Sajja

28 Created by Priti Srinivas Sajja
Bio-Inspired Computing New approaches to AI Taking inspiration form nature and biological systems Includes models such as Artificial Neural Network (ANN) Genetic Algorithm(GA) Swarm Intelligence(SI), etc. Nature has virtues of self learning, evolution, emergence and immunity The objective of bio-inspired models and techniques to take inspiration from Mother Nature and solve problems in more effective and intelligent way Bio-inspired Created by Priti Srinivas Sajja

29 Created by Priti Srinivas Sajja
Artificial Neural Network (ANN) An artificial neural network (ANN) is connectionist model of programming using computers. An ANN attempts to give computers humanlike abilities by mimicking the human brain’s functionality. The human brain consists of a network of more than a hundred billions interconnected neurons working in a parallel fashion. An artificial neuron X2 X1 XiWi W1 W2 … …. y Xn Wn A biological neuron Bio-inspired Created by Priti Srinivas Sajja

30 Going to Army: to Be or not to Be? A multilayer perceptron
Mom (0.3) Dad (0.5) ∑Wi Xi 0.6 0.4 Going to Army: to Be or not to Be? Importance to Mom Importance to Dad = 0.3* *0.4 = = which is < 0.6 W12 X1 X2 X3 . Xn O0 O1 …. Om W1h Input layer Hidden layers Output layer A multilayer perceptron Bio-inspired Created by Priti Srinivas Sajja

31 Evaluating new individuals through fitness function
Genetic Algorithms (GA) It mimics Nature’s evolutionary approach The algorithm is based on the process of natural selection—Charles Darwin’s “survival of the fittest.” GAs can be used in problem solving, function optimizing, machine learning, and in innovative systems. Genetic cycle Modify with operations Start with initial population by randomly selected Individuals Evaluate fitness of new individuals Update population with better individuals and repeat Initial population Selection Mutation Crossover Evaluating new individuals through fitness function Modify the population Bio-inspired Created by Priti Srinivas Sajja

32 Created by Priti Srinivas Sajja
Swarm Intelligence Inspired by the collective behavior of social insect colonies and other animal societies Ant colony, fish school, bird flocking and honey comb are the examples Bio-inspired Created by Priti Srinivas Sajja

33 Created by Priti Srinivas Sajja
Some more examples …. Natural Inspired Bio-inspired Created by Priti Srinivas Sajja

34 Example Fuzzy Interface Created by Priti Srinivas Sajja
Structure of proposed system Fuzzy interface Linguistic fuzzy interface Fuzzy rule base and membership functions Workspace Crisp Normalized values Decision support Users choice and needs Underlying ANN P1 P2 P3 P4 Implicit and self learning by ANN Friendly interface, Explicit justification, and Documentation Example Created by Priti Srinivas Sajja

35 Created by Priti Srinivas Sajja
Example Created by Priti Srinivas Sajja

36 This slideshow is available here

37 Created by Priti Srinivas Sajja
References llustrationsOf.com Prersentermedia.com Presentationmagazine.com Clikr.com Engadget.com scenicreflections.com lih.univ-lehavre.fr business2press.com globalswarminghoneybees.blogspot.com Knowledge-based systems, Akerkar RA and Priti Srinivas Sajja, Jones & Bartlett Publishers, Sudbury, MA, USA (2009) Acknowledgement Created by Priti Srinivas Sajja


Download ppt "Artificial Intelligence"

Similar presentations


Ads by Google