Introduction to Artificial Intelligence, Lecture notes of Artificial Intelligence

Download Introduction to Artificial Intelligence and more Lecture notes Artificial Intelligence in PDF only on Docsity! INTRODUCTION TO ARTIFICIAL UE ACID Objectives of this Course • This class is a broad introduction to artificial intelligence (AI) o AI is a very broad field with many subareas • We will cover many of the primary concepts/ideas • But in 15 weeks we can’t cover everything AI and SoftComputing ANN Learning and adaptation Fuzzy Set Theory Knowledge representation Via Fuzzy if-then RULE Genetic Algorithms Systematic Random Search AI Symbolic Manipulation AI and SoftComputing cat cut knowledge Animal? cat Neural character recognition 5 What is Hard Computing ? • Hard computing, i.e., conventional computing, requires a precisely stated analytical model and often a lot of Computational Time. • Many analytical models are valid for ideal cases. • Real world problems exist in a non-ideal environment. 8 Mobile robot Coordination weather forecasting Natural Language Processing What is Artificial Intelligence? Some Definitions (I) The exciting new effort to make computers think … machines with minds, in the full literal sense. Haugeland, 1985 Outline of the Course • Knowledge representation: o propositional logic and first-order logic o inference in Expert Systems o Fuzzy logic o Rough set o Machine learning: classification trees o Neural networks o Ohers ? What is ntelligence? • Intelligence: o ―the capacity to learn and solve problems‖ (Websters dictionary) o in particular, • the ability to solve novel problems • the ability to act rationally • the ability to act like humans • Artificial Intelligence o build and understand intelligent entities or agents o 2 main approaches: ―engineering‖ versus ―cognitivemodeling‖ What is Artificial Intelligence? (John McCarthy, Stanford University) • What isartificialintelligence? Itisthe science and engineering of making intelligentmachines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologicallyobservable. • Isn't there a solid definition of intelligence that doesn't depend on relating it to human intelligence? Not yet. The problem is that we cannot yet characterize in general what kinds of computational procedures we want to call intelligent.We understand some of the mechanismsof intelligence and not others. • More in:http://www-formal.stanford.edu/jmc/whatisai/node1.html History of AI • 1943: early beginnings o McCulloch & Pitts: Boolean circuit model of brain • 1950: Turing o Turing's "Computing Machinery and Intelligence― • 1956: birth of AI o Dartmouth meeting: "Artificial Intelligence― name adopted • 1950s: initial promise o Early AI programs, including o Samuel's checkers program o Newell & Simon's LogicTheorist History of AI • 1966—73: Reality dawns o Realization that many AI problems are intractable o Limitations of existing neural network methods identified • Neural network research almostdisappears • 1969—85: Adding domain knowledge o Development of knowledge-basedsystems o Success of rule-based expertsystems, • E.g., DENDRAL, MYCIN • But were brittle and did not scale well in practice • 1986-- Rise of machine learning o Neural networks return to popularity o Major advances in machine learning algorithms and applications • 1990-- Role of uncertainty o Bayesian networks as a knowledge representation framework • 1995--AI as Science o Integration of learning, reasoning, knowledgerepresentation o AI methods used in vision, language, data mining, etc Different Types of Artificial Intelligence 1.Modeling exactly how humans actually think 2.Modeling exactly how humans actually act 3.Modeling how ideal agents ―should think‖ 4.Modeling how ideal agents ―should act‖ • Modern AI focuses on the last definition o we will also focus on this ―engineering‖ approach o success is judged by how well the agent performs The Chinese Room Set of rules, in English, for transforming phrases Chinese Writing is given to the person Correct Responses She does not know Chinese The Chinese Room • So imagine an individual is locked in a room and given a batchof Chinese writing. • The person locked in the room does not understand Chinese. Next he is given more Chinese writing and a set of rules (in English which he understands) on how to collate the first set of Chinese characters with the second set of Chinese characters. • Suppose the person gets so good at manipulating the Chinese symbols and the rules are so good, that to those outside the room itappears that the personunderstandsChinese. • Searle's point is that, he doesn't really understand Chinese, it reallyonly following a setof rules. • Following this argument, a computer could never be truly intelligent, it is only manipulating symbols that it really doesn't understand the semanticcontext. Can these Questions are Answerable?  Can Computers play Humans at Chess?  Can Computers Talk?  Can Computers RecognizeSpeech?  Can Computers Learn and Adapt ?  Can Computers “see”?  Can Computers plan and make decisions? Can Computers Recognize Speech? • Speech Recognition: o mapping sounds from a microphone into a list of words o classic problemin AI, very difficult • Recognizing single words from a small vocabulary • systems can do this with high accuracy (order of 99%) • e.g., directory inquiries o limited vocabulary (area codes, city names) o computer tries to recognize you first, if unsuccessful hands you over to a human operator o saves millions of dollars a year for the phone companies Recognizing human speech (ctd.) • Recognizing normal speech is much more difficult o speech is continuous: where are the boundaries between words? • e.g., ―John’s car has a flat tire‖ o large vocabularies • can be many thousands of possible words • we can use context to help figure out what someone said o e.g., hypothesize and test o try telling a waiter in a restaurant: ―I would like some sugar in my coffee‖ o background noise, other speakers, accents, colds, etc o on normal speech, modern systems are only about 60-70%accurate • Conclusion: o NO, normal speech is too complex to accurately recognize o YES, for restricted problems (small vocabulary, singlespeaker) Can Computers Learn and Adapt ? • Learning and Adaptation o consider a computer learning to drive on the freeway o we could code lots of rules about what to do o and/or we could have it learn from experience o machine learning allows computers to learn to do things without explicit programming • Conclusion: YES, computers can learn and adapt, when presented with information in the appropriate way Can Computers plan and make decisions? • Intelligence o involves solving problems and making decisions and plans o e.g., you want to visit your cousin in Boston • you need to decide on dates, flights • you need to get to the airport, etc • involves a sequence of decisions, plans, and actions • What makes planninghard? o the world is notpredictable: • your flight is canceled or there’s a backup on the 405 o there is a potentially huge number of details • do you consider all flights? all dates? o no: commonsense constrains yoursolutions o AI systems are only successful in constrained planning problems • Conclusion: NO, real-world planning and decision- making is still beyond the capabilities of modern computers o exception: very well-defined, constrained problems: mission planning for satelites. Summary of State of AI Systems in Practice • Speech synthesis, recognition and understanding o very useful for limited vocabulary applications o unconstrained speech understanding is still too hard • Computer vision o works for constrained problems (hand-written zip-codes) o understanding real-world, natural scenes is still too hard • Learning o adaptive systemsare used in many applications: have their limits • Planning and Reasoning o only works for constrained problems: e.g., chess o real-world is too complex for general systems • Overall: o many components of intelligent systemsare ―doable‖ o there are many interesting research problems remaining Intelligent Systems in Your Everyday Life • Post Office o automatic address recognition and sorting of mail • Banks o automatic check readers, signature verification systems o automated loan applicationclassification • Telephone Companies o automatic voice recognition for directory inquiries • Credit Card Companies o automated fraud detection • Computer Companies o automated diagnosis for help-deskapplications • Netflix: o movie recommendation • Google: o Search Technology