Artificial Intelligence Introductory Lecture

Who Am I? Prof. Dr. Adeel Akram BSc Electrical Engg. MSc Computer Engg. PhD in Adhoc Wireless Networks Telecom Engineering Dept. UET, Taxila adeel.akram@uettaxila.edu.pk

What is artificial intelligence? Science and engineering of making intelligent machines, especially intelligent computer programs Using computers to understand human intelligence Not confined to methods that are biologically observable

What is intelligence? Intelligence is the computational part of the ability to achieve goals in the world. Degree of intelligence vary in people, animals and machines

Tighter definition of AI AI is the science of making machines do things that would require intelligence if done by people. (Minsky) At least we have experience with human intelligence Possible definition: intelligence is the ability to form plans to achieve goals by interacting with an information-rich environment Intelligence encompasses abilities such as: understanding language perception reasoning learning

Pre-history of AI the quest for understanding & automating intelligence has deep roots 4th cent. B.C.: Aristotle studied mind & thought, defined formal logic 14th–16th cent.: Renaissance thought built on the idea that all natural or artificial processes could be mathematically analyzed and understood 18th cent.: Descartes emphasized the distinction between mind & brain (famous for "Cogito ergo sum") 19th cent.: advances in science & understanding nature made the idea of creating artificial life seem plausible Shelley's Frankenstein raised moral and ethical questions Babbage's Analytical Engine proposed a general-purpose, programmable computing machine -- metaphor for the brain 19th-20th cent.: saw many advances in logic formalisms, including Boole's algebra, Frege's predicate calculus, Tarski's theory of reference 20th cent.: advent of digital computers in late 1940's made AI a viable Turing wrote seminal paper on thinking machines (1950)

Pre-history of AI (2) birth of AI occurred when Marvin Minsky & John McCarthy organized the Dartmouth Conference in 1956 brought together researchers interested in "intelligent machines" for next 20 years, virtually all advances in AI were by attendees Minsky (MIT), McCarthy (MIT/Stanford), Newell & Simon (Carnegie),…

AI aims to put the human mind into the computer? Some researchers say that !!! maybe they are using it metaphorically Human mind has a lot of peculiarities Nobody is serious about imitating them all

What is the Turing test? Alan Turing's 1950 article Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent He argued that if the machine could successfully pretend to be human to a knowledgeable observer then you certainly should consider it intelligent This test would satisfy most people but not all philosophers The observer could interact with the machine and a human by teletype The human would try to persuade the observer that it was human and the machine would try to fool the observer

Turing test (2) Turing test is a one-sided A machine that passes the test should certainly be considered intelligent, But a machine could still be considered intelligent without knowing enough about humans to imitate a human e.g., Weizenbaum's ELIZA program J. Weizenbaum, ”ELIZA -- A computer program for the study of natural language communication between man and machine", Communications of the ACM 9(1):36-45, 1966.

Aim of AI? The ultimate effort is to make computer programs that can solve problems and achieve goals in the world as well as humans do. However, many people involved in particular research areas are much less ambitious

human-level intelligence? A few people think that human-level intelligence can be achieved by writing large numbers of programs (of the kind people are now writing) and assembling vast knowledge bases of facts (in the languages now used for expressing knowledge)

human-level intelligence? When will it happen? Most AI researchers believe that new fundamental ideas are required, and therefore it cannot be predicted when human level intelligence will be achieved

History of AI (1) the history of AI research is a continual cycle of optimism & hype  reality check & backlash  refocus & progress  … 1950's – birth of AI, optimism on many fronts general purpose reasoning, machine translation, neural computing, … first neural net simulator (Minsky): could learn to traverse a maze GPS (Newell & Simon): general problem-solver/planner, means-end analysis Geometry Theorem Prover (Gelertner): input diagrams, backward reasoning SAINT(Slagle): symbolic integration, could pass MIT calculus exam

History of AI (2) 1960's – failed to meet claims of 50's, problems turned out to be hard! so, backed up and focused on "micro-worlds" within limited domains, success in: reasoning, perception, understanding, … ANALOGY (Evans & Minsky): could solve IQ test puzzle STUDENT (Bobrow & Minsky): could solve algebraic word problems SHRDLU (Winograd): could manipulate blocks using robotic arm, explain self STRIPS (Nilsson & Fikes): problem-solver planner, controlled robot "Shakey" Minsky & Papert demonstrated the limitations of neural nets

History of AI (3) 1970's – results from micro-worlds did not easily scale up so, backed up and focused on theoretical foundations, learning/understanding conceptual dependency theory (Schank) frames (Minsky) machine learning: ID3 (Quinlan), AM (Lenat) practical success: expert systems DENDRAL (Feigenbaum): identified molecular structure MYCIN (Shortliffe & Buchanan): diagnosed infectious blood diseases

History of AI (4) 1980's – BOOM TOWN! cheaper computing made AI software feasible success with expert systems, neural nets revisited, 5th Generation Project XCON (McDermott): saved DEC ~ $40M per year neural computing: back-propagation (Werbos), associative memory (Hopfield) logic programming, specialized AI technology seen as future

History of AI (5) 1990's – again, failed to meet high expectations so, backed up and focused : embedded intelligent systems, agents, … hybrid approaches: logic + neural nets + genetic algorithms + fuzzy + … CYC (Lenat): far-reaching project to capture common-sense reasoning Society of Mind (Minsky): intelligence is product of complex interactions of simple agents Deep Blue (formerly Deep Thought): defeated Kasparov in Speed Chess in 1997

Philosophical extremes in AI (1) Neats vs. Scruffies Neats focus on smaller, simplified problems that can be well-understood, then attempt to generalize lessons learned Scruffies tackle big, hard problems directly using less formal approaches

Philosophical extremes in AI (2) GOFAIs vs. Emergents GOFAI (Good Old-Fashioned AI) works on the assumption that intelligence can and should be modeled at the symbolic level Emergents believe intelligence emerges out of the complex interaction of simple, sub-symbolic processes

Philosophical extremes in AI (3) Weak AI vs. Strong AI Weak AI believes that machine intelligence need only mimic the behavior of human intelligence Strong AI demands that machine intelligence must mimic the internal processes of human intelligence, not just the external behavior

Criteria for success (1) long term: Turing Test (for Weak AI) as proposed by Alan Turing (1950), if a computer can make people think it is human (i.e., intelligent) via an unrestricted conversation, then it is intelligent Turing predicted fully intelligent machines by 2000, not even close Loebner Prize competition, extremely controversial

Criteria for success (2) short term: more modest success in limited domains performance equal or better than humans e.g., game playing (Deep Blue), expert systems (MYCIN) real-world practicality $$$ e.g., expert systems (XCON, Prospector), fuzzy logic (cruise control)

Criteria for success (3) AI is still a long way from its long term goal but in ~50 years, it has matured into a legitimate branch of science has realized its problems are hard has factored its problems into subfields is attacking simple problems first, but thinking big

Criteria for success (4) surprisingly, AI has done better at "expert tasks" as opposed to "mundane tasks" that require common sense & experience hard for humans, not for AI: e.g., chess, rule-based reasoning & diagnosis, easy for humans, not for AI: e.g., language understanding, vision, mobility, …

Course Material Text book: Artificial Intelligence: Structures and Strategies for Complex Problem Solving (4th ed.), George F. Luger, Addison-Wesley, 2002. Artificial Intelligence, A Modern Approach, Stuart Russell and Peter Norvig, Prentice Hall, ’95

AI Knowledge-based and Expert Systems Planning Coping with Vague, Incomplete and Uncertain Knowledge Searching Intelligently AI Logical Reasoning & Theorem Proving Communicating, Perceiving and Acting Intelligent Agents & Distributed AI Learning & Knowledge Discovery

Course goals Survey the field of Artificial Intelligence, including major areas of study and research Study the foundational concepts and theories that underlie AI, including search, knowledge representation, and sub-symbolic models Contrast the main approaches to AI: symbolic vs. emergent Provide practical experience developing AI systems using the logic programming language Prolog

Course outline Logic and Prolog Problem-solving as search predicate calculus logic programming, Prolog Problem-solving as search state spaces search strategies, heuristics game playing Knowledge representation & reasoning representation structures (semantic nets, frames, scripts, …) expert systems, uncertainty automated reasoning Machine learning symbolic models: candidate elimination, ID3 connectionist models: neural nets, backprop, associative memory emergent models: genetic algorithms, artificial life Selected AI topics student presentations

Next Lecture… logic & logic programming Read Chapters 1, 2 & 14 propositional calculus, predicate calculus logic programming Prolog basics Read Chapters 1, 2 & 14 Be prepared for a quiz on today’s lecture (moderately thorough)

Questions & Answers ???????