Course Overview and Introduction CE417: Introduction to Artificial Intelligence Sharif University of Technology Spring 2019 Soleymani Some slides have been adopted from: - Klein and Abdeel, CS188, UC Berkeley. - Sandholm, 15381, CMU.
Course Info } Instructor: M. Soleymani } Email: soleymani@sharif.edu } Head TA: Parishad Behnam Ghader } Website: http://ce.sharif.edu/cources/97-98/2/ce417-2 } Discussions: On Piazza 2
Text Book Artificial Intelligence:A Modern Approach by Stuart Russell and Peter Norvig 3 rd Edition, 2009 http://aima.cs.berkeley.edu/ 3
Marking Scheme } Mid Term Exam: 25% } Final Exam: 30% } Mini-exams: 10% } Homeworks (written & programming): 30% } Four or five quizzes: 5% 4
Today } What is artificial intelligence? } What can AI do? } What is this course? 5
Sci-Fi AI? 6
Formal Definitions of Artificial Intelligence Human intelligence Rational Thinking Thinking humanly Thinking rationally Behavior Acting humanly Acting rationally 7
What is AI? The science of making machines that: Think like people Think rationally Act like people Act rationally 8
What is AI? The science of making machines that: Think like people Think rationally Act like people Act rationally 9
What About the Brain? § Brains (human minds) are very good at making rational decisions, but not perfect § Brains aren’t as modular as software, so hard to reverse engineer! § “Brains are to intelligence as wings are to flight” § Lessons learned from the brain: memory and simulation are key to decision making 10
Acting Humanly } Turing Test (Turing, 1950): Operational test for intelligent behavior: } A human interrogator communicates (through a teletype) with a hidden subject that is either a computer system or a human. If the human interrogator cannot reliably decide whether or not the subject is a computer, the computer is said to have passed the Turing test. } 5 minutes test, it passes by fooling the interrogator 30% of time } Turing predicted that by 2000 a computer could pass the test. } He was wrong. 11
Rational Decisions } Turing Test (Turing, 1950): Operational test for intelligent behavior: } We’ll use the term rational in a very specific, technical way } Rational: maximally achieving pre-defined goal } Rationality only concerns what decisions are made (not the thought process behind them) } Goals are expressed in terms of the utility of outcome } Being rational means maximizing your expected utility A better title for this course would be: Computational Rationality 12
Maximize Your Expected Utility 13
Designing Rational Agents An agent is an entity that perceives and acts . } A rational agent selects actions that maximize its } (expected) utility . Characteristics of the percepts, environment, } and action space dictate techniques for selecting rational actions Environment Sensors Percepts Agent ? Actuators Actions 14
A (Short) History of AI 15
A (Short) History of AI 1940-1950: Early days } 1943: McCulloch & Pitts: Boolean circuit model of brain } 1950: Turing's “Computing Machinery and Intelligence” } 1950—70: Excitement: Look, Ma, no hands! } 1950s: Early AI programs, including Samuel's checkers program, Newell } & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “Artificial Intelligence” adopted } 1965: Robinson's complete algorithm for logical reasoning } 1970—90: Knowledge-based approaches } 1969—79: Early development of knowledge-based systems } 1980—88: Expert systems industry booms } 1988—93: Expert systems industry busts: “AI Winter” } 1990—: Scientific method (Statistical approaches) } Resurgence of probability, focus on uncertainty } General increase in technical depth } Agents and learning systems… “AI Spring”? } 2000—:Where are we now? } 16
Birth of AI: 1943-1956 17
A (Short) History of AI 1940-1950: Early days } 1943: McCulloch & Pitts: Boolean circuit model of brain } 1950: Turing's “Computing Machinery and Intelligence” } 1950—70: Excitement: Look, Ma, no hands! } 1950s: Early AI programs, including Samuel's checkers program, Newell } & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “Artificial Intelligence” adopted } 1965: Robinson's complete algorithm for logical reasoning } 1970—90: Knowledge-based approaches } 1969—79: Early development of knowledge-based systems } 1980—88: Expert systems industry booms } 1988—93: Expert systems industry busts: “AI Winter” } 1990—: Scientific method (Statistical approaches) } Resurgence of probability, focus on uncertainty } General increase in technical depth } Agents and learning systems… “AI Spring”? } 2000—:Where are we now? } 18
Early successes: 1950s-1960s -> A* algorithm 19
First AI Winter: Late 1970s 20
A (Short) History of AI 1940-1950: Early days } 1943: McCulloch & Pitts: Boolean circuit model of brain } 1950: Turing's “Computing Machinery and Intelligence” } 1950—70: Excitement: Look, Ma, no hands! } 1950s: Early AI programs, including Samuel's checkers program, Newell } & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “Artificial Intelligence” adopted } 1965: Robinson's complete algorithm for logical reasoning } 1970—90: Knowledge-based approaches } 1969—79: Early development of knowledge-based systems } 1980—88: Expert systems industry booms } 1988—93: Expert systems industry busts: “AI Winter” } 1990—: Scientific method (Statistical approaches) } Resurgence of probability, focus on uncertainty } General increase in technical depth } Agents and learning systems… “AI Spring”? } 2000—:Where are we now? } 21
Expert Systems and Business (1970s-1980s) 22
A (Short) History of AI 1940-1950: Early days } 1943: McCulloch & Pitts: Boolean circuit model of brain } 1950: Turing's “Computing Machinery and Intelligence” } 1950—70: Excitement: Look, Ma, no hands! } 1950s: Early AI programs, including Samuel's checkers program, Newell } & Simon's Logic Theorist, Gelernter's Geometry Engine 1956: Dartmouth meeting: “Artificial Intelligence” adopted } 1965: Robinson's complete algorithm for logical reasoning } 1970—90: Knowledge-based approaches } 1969—79: Early development of knowledge-based systems } 1980—88: Expert systems industry booms } 1988—93: Expert systems industry busts: “AI Winter” } 1990—: Scientific method (Statistical approaches) } Resurgence of probability, focus on uncertainty } General increase in technical depth } Agents and learning systems… “AI Spring”? } 2000—:Where are we now? } 23
Focus on Applications (1990s-2010s) 24
Reemergence of AI (2010s-??) 2015-2017 – superhuman speech understanding 25
Current Applications of AI 26
Superhuman strategic reasoning under imperfect information Libratus beats best humans at heads-up no-limit Texas hold’em poker [Brown & Sandholm] Pittsburgh, January 2017 Haikou, April 2017 27
AI is that which appears in academic conferences of AI 28
AI is that which appears in academic conferences of AI 29
AI is that which appears in academic conferences of AI 30
AI is that which appears in academic conferences of AI 31
AI } We won’t worry too much about definition of AI, but the following will suffice: } AI is the development and study of computing systems that address a problem typically associated with some form of intelligence } AI is a fast-moving exciting area } We can directly make the world a better place using AI 32
What Can AI Now Do? Quiz:Which of the following can be done at present? Play a decent game of table tennis? } Play a decent game of Jeopardy? } Drive safely along a curving mountain road? } Drive safely alongT elegraph Avenue? } Buy a week's worth of groceries on the web? } Buy a week's worth of groceries at Berkeley Bowl? } Discover and prove a new mathematical theorem? } Converse successfully with another person for an hour? } Perform a surgical operation? } Put away the dishes and fold the laundry? } Translate spoken Chinese into spoken English in real time? } Write an intentionally funny story? } 33
Natural Language } Speech technologies (e.g. Siri) Automatic speech recognition (ASR) } T ext-to-speech synthesis (TTS) } Dialog systems } 34
Natural Language } Speech technologies (e.g. Siri) Automatic speech recognition (ASR) } T ext-to-speech synthesis (TTS) } Dialog systems } } Language processing technologies Question answering } Machine translation } T ext classification, spam filtering, etc… } Web search } 35
Vision (Perception) § Object and face recognition § Scene segmentation § Image classification Image from: A. Krizhevsky et. al, ImageNet Classification with Deep Convolutional 36 Neural Networks, NIPS 2012.
Robotics } Robotics Part mech. eng. } Part AI } Reality much } harder than simulations! } Technologies Vehicles } Rescue } Soccer! } Lots of automation… } } In this class: We ignore mechanical aspects } Methods for planning } Methods for control } Images from UC Berkeley, Boston Dynamics, RoboCup, Google 37
Recommend
More recommend
