1/15 FOUNDATIONS OF ARTIFICIAL INTELLIGENCE Introduction: Chapter 1.

Slides:



Advertisements
Similar presentations
CSCI 4800 ARTIFICIAL INTELLIGENCE
Advertisements

Artificial Intelligence: Introduction
ARTIFICIAL INTELLIGENCE
Additional Topics ARTIFICIAL INTELLIGENCE
Artificial Intelligence
Artificial Intelligence An Introductory Course. Outline 1.Introduction 2.Problems and Search 3.Knowledge Representation 4.Advanced Topics.
CMPT 310: SUMMER 2011 OLIVER SCHULTE Introduction to Artificial Intelligence.
AI 授課教師:顏士淨 2013/09/12 1. Part I & Part II 2  Part I Artificial Intelligence 1 Introduction 2 Intelligent Agents Part II Problem Solving 3 Solving Problems.
Artificial Intelligence Computational Intelligence Alien Intelligence? Summer 2004 Dennis Kibler.
Artificial Intelligence A Modern Approach Dennis Kibler.
CPSC 7373: Artificial Intelligence Jiang Bian, Fall 2014 University of Arkansas for Medical Sciences University of Arkansas at Little Rock.
CS 332: Introduction to AI Class Hour: Section 1: MWF 1:10PM - 2:00PM. Hyer 210.
ICS-171:Notes 1: 1 Welcome to CompSci 171 Fall 2010 Introduction to AI. Instructor:Max Welling, Office hours:Wed. 4-5pm in BH
CS 531/331: Introduction to AI
PSU CS 370 – Artificial Intelligence Dr. Mohamed Tounsi Artificial Intelligence 1. Introduction Dr. M. Tounsi.
Overview of Artificial Intelligence (AI)
CSE 471/598,CBS598 Introduction to Artificial Intelligence Fall 2004
CS 480 Lec 2 Sept 4 complete the introduction Chapter 3 (search)
INSTRUCTOR: DR. XENIA MOUNTROUIDOU CS CS Artificial Intelligence.
ARTIFICIAL INTELLIGENCE Introduction: Chapter Textbook: S. Russell and P. Norvig Artificial Intelligence: A Modern Approach Prentice Hall, 2003,
Artificial Intelligence
Greg GrudicIntroduction to AI1 Introduction to Artificial Intelligence CSCI 3202 Fall 2007 Greg Grudic.
ARTIFICIAL INTELLIGENCE
1 Artificial Intelligence An Introductory Course.
CPSC 171 Artificial Intelligence Read Chapter 14.
Artificial Intelligence
FOUNDATIONS OF ARTIFICIAL INTELLIGENCE Introduction: Chapter 1.
ARTIFICIAL INTELLIGENCE Introduction: Chapter 1. Outline Course overview What is AI? A brief history The state of the art.
CSW 4701 AI Spring 2013 Introduction: Chapter Course home page: Textbook: S. Russell and P. Norvig.
1 AI and Agents CS 171/271 (Chapters 1 and 2) Some text and images in these slides were drawn from Russel & Norvig’s published material.
CISC4/681 Introduction to Artificial Intelligence1 Introduction – Artificial Intelligence a Modern Approach Russell and Norvig: 1.
Introduction: Chapter 1
Introduction: Structure and Overview What is AI Systems that think like humans Systems that think rationally Systems that act rationally Systems that act.
Artificial Intelligence: An Introduction Definition of AI Foundations of AI History of AI Advanced Techniques.
CSC4444: Artificial Intelligence Fall 2011 Dr. Jianhua Chen Slides adapted from those on the textbook website.
IFT3335 – Intruduction à l’intelligence artrificielle basé sur le cours de NUS et Berkeley Introduction: Chapter 1.
CNS 4470 Artificial Intelligence. What is AI? No really what is it? No really what is it?
Inteligenica Artificial FIE - UMSNH. Semestre 9 Introduccion: Capitulo 1.
Text Book Outline. Outline Introduction –Chapter 1: Introduction –Chapter 2: Intelligent agents Problem solving –Chapter 3: Solving problems by searching.
Artificial Intelligence CS 363 Kawther Abas Lecture 1 Introduction 5/4/1435.
ARTIFICIAL INTELLIGENCE 2009 Ira Pohl TIM Oct 29, 2009.
Lecture 1 – AI Background Dr. Muhammad Adnan Hashmi 1.
Introduction to Artificial Intelligence Mitch Marcus CIS391 Fall, 2008.
ARTIFICIAL INTELLIGENCE 2006 Ira Pohl TIM Feb 23, 2006.
Artificial Intelligence
So what is AI?.
1 Lecture # 1 Introduction to Artificial Intelligence By NADEEM MAHMOOD ASSISTANT PROFESSOR DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF KARACHI.
Lecture 1 – AI Background Dr. Muhammad Adnan Hashmi 1.
What is Artificial Intelligence? What is artificial intelligence? It is the science and engineering of making intelligent machines, especially intelligent.
Definitions Think like humansThink rationally Act like humansAct rationally The science of making machines that: This slide deck courtesy of Dan Klein.
What is Artificial Intelligence?
FOUNDATIONS OF ARTIFICIAL INTELLIGENCE
1 Introduction to Artificial Intelligence MSc WS 2009 Organisation + Introduction: Chapter 1.
Artificial Intelligence Lecture 2 Department of Computer Science, International Islamic University Islamabad, Pakistan.
Princess Nora University Artificial Intelligence CS 461 Level 8 1.
1 Artificial Intelligence & Prolog Programming CSL 302.
Artificial Intelligence Lecture 1. Introduction. Course Outline The course consists of:  15 lectures slots (may use some for tutorials);  tutorial exercises;
CSC 450 Artificial Intelligence. W HAT IS AI? Thinking humanlyThinking rationally Acting humanlyActing rationally Revision!...
CMPT 310 OLIVER SCHULTE Introduction to Artificial Intelligence.
Artificial Intelligence
CSC 290 Introduction to Artificial Intelligence
Artificial Intelligence: Definition
CS4341 Introduction to Artificial Intelligence
Artificial Intelligence Lecture 2: Foundation of Artificial Intelligence By: Nur Uddin, Ph.D.
AI and Agents CS 171/271 (Chapters 1 and 2)
CS 404 Artificial Intelligence
Hong Cheng SEG4560 Computational Intelligence for Decision Making Chapter 1: Introduction Hong Cheng
Artificial Intelligence
Artificial Intelligence
Presentation transcript:

1/15 FOUNDATIONS OF ARTIFICIAL INTELLIGENCE Introduction: Chapter 1

2/15 Why AI Humans and animals can solve many complex problems, can we use or get idea from these approaches? How humans think?

تکلیف 1 1- یک راهکار برای انتخاب عمل در هر مرحله در بازی دوز بیان کنید. (شبه کد را بنویسید). 2- یک روش تعیین حرکت برای محیط شطرنج با دو بازیگر در نظر بگیرید و یک الگوریتم انجام حرکت برای یک بازیکن بنویسید. 3- مقدار x,y را پیدا کنید به گونه ای که تابع زیر حداقل گردد. 3/15

تکلیف 1(ادامه) 4- راهی برای مدلسازی دانش یک راننده یا پزشک یا خبره اقتصادی بیان کنید. 5- فرض کنید نقشه جغرافیایی ایران را دارید، و قرار است کامپیوتر کوتاهترین راه برای رسیدن از یزد به مشهد را بیابد راهتان را بیان کنید. 4/15

5/15 What is AI? Views of AI fall into four categories: Rationality:A system is rational if it does the "right thing," given what it knows. The textbook advocates "acting rationally" Thinking Humanly تلاش برای اینکه کامیپوترها مانندانسان فکر کنند Thinking rationally مطالعه قدرت ذهنی با استفاده از مدلهای محاسباتی Acting humanly هنر خلق ماشینهایی که مانند انسان عمل کنند Acting rationally هوش محاسباتی مطالعه برای طراحی عالمهای هوشمند است

6/15 Acting humanly: Turing Test Turing (1950) "Computing machinery and intelligence": "Can machines think?"  "Can machines behave intelligently?" Operational test for intelligent behavior: the Imitation Game Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes شش قابلیت لازم : پردازش زبان طبیعی، بازنمایی دانش، استدلال خودکار، یادگیری ماشینی، بینایی، ربات توجه: همه انسانها عملکرد عالی (perfect) ندارند.

7/15 Thinking humanly: cognitive modeling برای اینکه بفهمیم یک انسان چگونه فکر میکند سه راه است: –درون نگری : ثبت افکارمان –آزمایشهای روانشناسی: مشاهده رفتار یک انسان در عمل –تصویر برداری از مغز: مشاهده مغر در عمل 1960s "cognitive revolution": information-processing psychology Requires scientific theories of internal activities of the brain -- How to validate? Requires 1) Predicting and testing behavior of human subjects (top-down) or 2) Direct identification from neurological data (bottom-up) Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now distinct from AI

8/15 Thinking rationally: "laws of thought" Aristotle: what are correct arguments/thought processes? His syllogisms provided patterns for argument structures that always yielded correct conclusions when given correct premises Direct line through mathematics and philosophy to modern AI Problems: 1- it is not easy to take informal knowledge and state it in the formal terms required by logical notation, 2- ،There is a big difference between being able to solve a problem "in principle" and doing so in practice.

9/15 Acting rationally: rational agent Rational behavior: doing the right thing The right thing: that which is expected to maximize goal achievement, given the available information. استنتاج صحیح همه عقلانیت نیست: موقعیتهایی است که هیچ کار خوب قابل اثباتی برای انجام دادن وجود ندارد لیکن باید اقدامی انجام شود. بعضی از عملهای عقلانی نیاز به استنتاج ندارند: مانند: عقب کشیدن دست از یک اجاق داغ

مزایای عامل عقلانی نسبت به بقیه بسیار کلی تر از ”قوانین تفکر“ است استنتاج صحیح تنها یکی از چند سازو کار رسیدن به عقلانیت در مقایسه با رویکرد رفتار یا تفکر انسانی، بسیار بیشتر تابع علم است. –استاندارد آن به وضوح تعریف شده و کامل است. 10/15

11/15 Rational agents An agent is an entity that perceives and acts This course is about designing rational agents Abstractly, an agent is a function from percept histories to actions: [f: P*  A ] For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance

12/15 AI prehistory PhilosophyLogic, methods of reasoning, mind as physical system foundations of learning, language, rationality MathematicsFormal representation and proof algorithms, computation, (un)decidability, (in)tractability, probability Economicsutility, decision theory Neurosciencephysical substrate for mental activity Psychology phenomena of perception and motor control, experimental techniques Computer building fast computers engineering Control theorydesign systems that maximize an objective function over time Linguisticsknowledge representation, grammar

13/15

14/15 short history of AI 1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turing's "Computing Machinery and Intelligence" 1956Dartmouth meeting: "Artificial Intelligence" adopted 1952—69Look, Ma, no hands! 1950sEarly AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1965Robinson's complete algorithm for logical reasoning 1966—73AI discovers computational complexity Neural network research almost disappears 1969—79Early development of knowledge-based systems: Dendral AI becomes an industry : R1 expert system Neural networks return to popularity AI becomes a science The emergence of intelligent agents

15/15 State of the art Robotic vehicles: رباتی بنام استندلی بدون رانده با سرعت 22 مایل در ساعت در صحرا حرکت کرد. Speech recognition Autonomous planning and scheduling: A hundred million miles from Earth, NASA's Remote Agent program became the first on-board autonomous planning program to control. Game Playing: Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997 Spam Fighting Logistic Planning: During the Persian Gulf crisis (1991) U.S. forces deployed a Dynamic analysis and replanning tool (DART) to do automated logistics and planning and scheduling for transportation (50,000 vehicles, cargo, people at a time)