CSC384: Intro To Artificial Intelligence

3y ago
87 Views
4 Downloads
273.44 KB
28 Pages
Last View : 7d ago
Last Download : 4m ago
Upload by : Rafael Ruffin
Transcription

Welcome to CSC384: Intro to Artificial Intelligence!@#!, MAN.Sheila McIlraith, University of Toronto, Winter 20111

CSC384: Intro to Artificial IntelligenceWinter 2011Instructor: Prof. Sheila McIlraithLectures/Tutorials: Monday1-2pm Wednesday 1-2pm Friday*1-2pmGB 221GB 221GB 244*The Friday hour will be a continuation of the lecture periodand/or time to go over extra examples and questions. Don’tplan to miss it!Sheila McIlraith, University of Toronto, Winter 20112

CSC384: TextbookRecommended Text:Artificial Intelligence: A Modern ApproachStuart Russell and Peter Norvig.3rd Edition, 2010. 2 copies of are on 24hr reserve in the Engineering andComputer Science Library. Recommended but not required. Lecture notes cover much of the course material and will beavailable online before class. Electronic version available online at a reduced price.3rd edition:Additional Reference:Computational Intelligence: A Logical ApproachDavid Poole, Alan Mackworth & Randy Goebel.2nd editionSheila McIlraith, University of Toronto, Winter 20113

CSC384: Prerequisites Prerequisites will not be checked for this course, exceptfor the CGPA (cumulative grade point average). You don’t need to request a waiver. You should have a stats course either the standardSTA 247/255/257 or at least something like STA 250. You need to have some familiarity with Prolog, CSC324 is thestandard prerequisite. We will provide 1 tutorial on Prolog. In all cases if you do not have the standard prerequisites *youwill be responsible* for covering any necessary background onyour own.Sheila McIlraith, University of Toronto, Winter 20114

CSC384: Website Course web sitehttp://www.cs.toronto.edu/ sheila/384/w11/ Primary source of more detailed information, announcements, etc. Check the site often (at least every one or two days). Updates about assignments, clarifications etc. will also be posted onthe web site. Course bulletin board (will not be oard CSC384H1SSheila McIlraith, University of Toronto, Winter 20115

CSC384: E-mail/board policies The course bulletin board will not be moderated. It can be used to communicate with your fellow students. Do not send questions there that you want answered by the instructor.Send e-mail directly. For each assignment, a TA will be assigned to answer questions.Please send your questions about each assignment to the TA. Answers that are important to everyone will be posted to the web site. Send only Plain Text (no HTML/MIME) using your CDF accounts. Start the subject of all your emails with “[CSC384]”.Please see:http://www.cs.toronto.edu/ sheila/384/w10/contactpolicy.htm A silent period will take effect 24 hours before each assignment is due.I.e. no question related to the assignment will be answered during thisperiod.Sheila McIlraith, University of Toronto, Winter 20116

CSC384: How you will be gradedCourse work: 3 Assignments (mostly programming, some short answer) (12% each) 2 term tests (17% each) 1 final exam (30% each) Assignments are worth a total of 36% Term tests are worth a total of 34% Final exam is worth a total of 30%Late Policy/Missing Test: You will have 2 grace days. Use them wisely! After that, you will be penalized for late assignments. For some assignments there may be a cut-off date after which assignmentswill no longer be accepted.Plagiarism: (handing of work not substantially the student’s own)http://www.cs.toronto.edu/ fpitt/documents/plagiarism.htmlSheila McIlraith, University of Toronto, Winter 20117

Artificial Intelligence (AI)How to achieve intelligent behaviourthrough computational meansSheila McIlraith, University of Toronto, Winter 201188

For most people AI evokes:Sheila McIlraith, University of Toronto, Winter 201199

But intelligence need not beembodied (Remember “Big Blue”) or it could be embodied in waysthat are not in keeping with ournotion of an intelligent being.Sheila McIlraith, University of Toronto, Winter 20111010

Are these intelligent?Sheila McIlraith, University of Toronto, Winter 20111111

What about these?Sheila McIlraith, University of Toronto, Winter 20111212

Subareas of AI Perception: vision, speech understanding, etc. Machine Learning, Neural network Robotics Natural language understanding Reasoning and decision making Í OUR FOCUS Knowledge representation Reasoning (logical, probabilistic) Decision making (search, planning, decision theory)Sheila McIlraith, University of Toronto, Winter 201113

Cognitive Robotics Endow robots, (immobots, software agents) with the ability toreason “soundly” about some aspect of the world. To do so with higher-level cognitive functions that involvereasoning about goals, perception, actions, and the mental statesof other agents. Endow them with some form of commonsense reasoning:The reasoning that tells you that Things usually fall down; When a child is crying they are likely upset and need comforting; If you’re travelling to San Francisco then your right eyeball islikely travelling with you!Sheila McIlraith, University of Toronto, Winter 20111414

but how do we buildartificial intelligences?Sheila McIlraith, University of Toronto, Winter 20111515

ActThinkIs Imitating Humans the Goal?Like humansNot necessarily like humansSystems that think likehumansSystems that think rationallySystems that act likehumansSystems that act rationallySheila McIlraith, University of Toronto, Winter 201116

Human Intelligence The Turing Test: A human interrogator. Communicates with a hidden subject that iseither a computer system or a human. If the human interrogatorcannot reliably decide whether on not the subject is a computer, thecomputer is said to have passed the Turing test. Turing provided some very persuasive arguments that asystem passing the Turing test is intelligent. However, the test does not provide much traction on thequestion of how to actually build an intelligent system.Sheila McIlraith, University of Toronto, Winter 201117

Human intelligence In general there are various reasons why trying to mimichumans might not be the best approach to AI: Computers and Humans have a very different architecture with quitedifferent abilities. Numerical computations Visual and sensory processing Massively and slow parallel vs. fast serialComputerHuman BrainComputational Units1 CPU, 108 gates1011 neuronsStorage Units1011 bits RAM1012 bits disk1011 neurons1014 synapsesCycle time10-9 sec10-3 secBandwidth1010 bits/sec1014 bits/secMemory updates/sec1091014Sheila McIlraith, University of Toronto, Winter 201118

Human Intelligence But more importantly, we know very little about how thehuman brain performs its higher level processes. Hence,this point of view provides very little information fromwhich a scientific understanding of these processes canbe built. However, Neuroscience has been very influential in someareas of AI. For example, in robotic sensing, visionprocessing, etc.Sheila McIlraith, University of Toronto, Winter 201119

Rationality The alternative approach relies on the notion ofrationality. Typically this is a precise mathematical notion ofwhat it means to do the right thing in any particularcircumstance. Provides A precise mechanism for analyzing and understanding theproperties of this ideal behaviour we are trying to achieve. A precise benchmark against which we can measure thebehavior the systems we build.Sheila McIlraith, University of Toronto, Winter 201120

Rationality Mathematical characterizations of rationality have come fromdiverse areas like logic (laws of thought) and economics(utility theory how best to act under uncertainty, game theoryhow self-interested agents interact). There is no universal agreement about which notion ofrationality is best, but since these notions are precise we canstudy them and give exact characterizations of theirproperties, good and bad. We’ll focus on acting rationally this has implications for thinking/reasoningSheila McIlraith, University of Toronto, Winter 201121

Computational Intelligence AI tries to understand and model intelligence as acomputational process. Thus we try to construct systems whosecomputation achieves or approximates the desirednotion of rationality. Hence AI is part of Computer Science. Other areas interested in the study of intelligence lie inother areas or study, e.g., cognitive science which focuseson human intelligence. Such areas are very related, buttheir central focus tends to be different.Sheila McIlraith, University of Toronto, Winter 201122

Degrees of Intelligence Building an intelligent system as capable as humansremains an elusive goal. However, systems have been built which exhibit variousspecialized degrees of intelligence. Formalisms and algorithmic ideas have been identified asbeing useful in the construction of these “intelligent”systems. Together these formalisms and algorithms form thefoundation of our attempt to understand intelligence as acomputational process. In this course we will study some of these formalisms andsee how they can be used to achieve various degrees ofintelligence.Sheila McIlraith, University of Toronto, Winter 201123

What We Cover in CSC384 Search Heuristic Search. (Chapter 3,4) Search spaces Heuristic guidance Backtracking Search (Chapter 5) “Vector of features” representation Case analysis search Game tree search (Chapter 6) Working against an opponentSheila McIlraith, University of Toronto, Winter 201124

What We Cover in CSC384 (cont.) Knowledge Representation (Chapter 7-10) First order logic for more general knowledge Knowledge represented in declarative manner Planning (Chapter 11-12) Predicate representation of states Planning graph Uncertainty (Chapter 13-16) Probabilistic reasoning, Bayes networks Utilities and influence diagrams Temporal probabilistic reasoning (?)Sheila McIlraith, University of Toronto, Winter 201125

Further Courses in AI CSC321H“Introduction to Neural Networks and Machine Learning” CSC401H1 “Natural Language Computing” CSC411H“Machine Learning and Data Mining” CSC412H1 “Uncertainty and Learning in Artificial Intelligence” CSC420H1 “Introduction to Image Understanding” CSC485H1 “Computational Linguistics” CSC486H1 “Knowledge Representation and Reasoning” CSC487H1 “Computational Vision”Sheila McIlraith, University of Toronto, Winter 201126

For Next Day Read Chapters 1 and 2 of Russell & Norvig Start reviewing Prolog tutorial material posted online Friday’s class will be a Prolog tutorial (most likely an online demo)Sheila McIlraith, University of Toronto, Winter 201127

Next Class: Romanian Travel.Currently in Arad, need to get to Bucharest bytomorrow to catch a flight.Sheila McIlraith, University of Toronto, Winter 201128

Artificial Intelligence: A Modern Approach Stuart Russell and Peter Norvig. 3rd Edition, 2010. 2 copies of are on 24hr reserve in the Engineering and Computer Science Library. Recommended but not required. Lecture notes cover much of the course material and will be available online before class.

Related Documents:

Artificial Intelligence -a brief introduction Project Management and Artificial Intelligence -Beyond human imagination! November 2018 7 Artificial Intelligence Applications Artificial Intelligence is the ability of a system to perform tasks through intelligent deduction, when provided with an abstract set of information.

and artificial intelligence expert, joined Ernst & Young as the person in charge of its global innovative artificial intelligence team. In recent years, many countries have been competing to carry out research and application of artificial intelli-gence, and the call for he use of artificial

BCS Foundation Certificate in Artificial Intelligence V1.1 Oct 2020 Syllabus Learning Objectives 1. Ethical and Sustainable Human and Artificial Intelligence (20%) Candidates will be able to: 1.1. Recall the general definition of Human and Artificial Intelligence (AI). 1.1.1. Describe the concept of intelligent agents. 1.1.2. Describe a modern .

IN ARTIFICIAL INTELLIGENCE Stuart Russell and Peter Norvig, Editors FORSYTH & PONCE Computer Vision: A Modern Approach GRAHAM ANSI Common Lisp JURAFSKY & MARTIN Speech and Language Processing, 2nd ed. NEAPOLITAN Learning Bayesian Networks RUSSELL & NORVIG Artificial Intelligence: A Modern Approach, 3rd ed. Artificial Intelligence A Modern Approach Third Edition Stuart J. Russell and Peter .

Peter Norvig Prentice Hall, 2003 This is the book that ties in most closely with the module Artificial Intelligence (2nd ed.) Elaine Rich & Kevin Knight McGraw Hill, 1991 Quite old now, but still a good second book Artificial Intelligence: A New Synthesis Nils Nilsson Morgan Kaufmann, 1998 A good modern book Artificial Intelligence (3rd ed.) Patrick Winston Addison Wesley, 1992 A classic, but .

BCS Essentials Certificate in Artificial Intelligence Syllabus V1.0 BCS 2018 Page 10 of 16 Recommended Reading List Artificial Intelligence and Consciousness Title Artificial Intelligence, A Modern Approach, 3rd Edition Author Stuart Russell and Peter Norvig, Publication Date 2016, ISBN 10 1292153962

PA R T 1 Introduction to Artificial Intelligence 1 Chapter 1 A Brief History of Artificial Intelligence 3 1.1 Introduction 3 1.2 What Is Artificial Intelligence? 4 1.3 Strong Methods and Weak Methods 5 1.4 From Aristotle to Babbage 6 1.5 Alan Turing and the 1950s 7 1.6 The 1960s to the 1990s 9 1.7 Philosophy 10 1.8 Linguistics 11

ABR ¼ American Board of Radiology; ARRS ¼ American Roentgen Ray Society; RSNA ¼ Radiological Society of North America. Table 2 Designing an emergency radiology facility for today Determine location of radiology in the emergency department Review imaging statistics and trends to determine type and volume of examinations in emergency radiology Prepare a comprehensive architectural program .