Introduction to AI Russell and Norvig: Chapters 1 and 2
Introduction to AI2 Found on the Web … AI is the reproduction of the methods of human reasoning or intuition Using computational models to simulate intelligent (human) behavior and processes AI is the study of mental faculties through the use computational methods Intelligent behavior Humans Computer
Introduction to AI3 I personally think that AI started as a rebellion against some form of establishment telling us “Computers cannot perform certain tasks requiring intelligence” For example, for many years AI researchers have regarded computational complexity theory as irrelevant to their field. They eventually had to reckon with it, but in the meantime computational complexity had also changed a lot.
Introduction to AI4 What is AI? Discipline that systematizes and automates intellectual tasks to create machines that: Act like humansAct rationally Think like humansThink rationally
Introduction to AI5 Act Like Humans AI is the art of creating machines that perform functions that require intelligence when performed by humans Methodology: Take an intellectual task at which people are better and make a computer do it Turing test Prove a theorem Play chess Plan a surgical operation Diagnose a disease Navigate in a building
Introduction to AI8 나비가 나는 이유 ? 나비는 유체역학적으로 날 수가 없다. 그러나 나비는 그 사실을 모르기 때문에 날 수 있다. 나비는 유체역학적으로 날기에 부적합하다. 제비는 적합하다. 그러나 나비는 제비 못지않게 잘 번성하고 있다. 나비처럼 나는 것도 이유가 있다. 어떤 나비는 미국에서 호주까지 날아가기도 한다. 흉내보다는 같은 기능을 하면 충분 !! 두 발로 걷는 로봇 ? 지네 같은 로봇 ?
Introduction to AI10 Think Like Humans How the computer performs functions does matter Comparison of the traces of the reasoning steps Cognitive science testable theories of the workings of the human mind But, do we want to duplicate human imperfections?
Introduction to AI11 Think/Act Rationally Always make the best decision given what is available (knowledge, time, resources) A performance measure is required 객관적인가 ? 청소로봇, 보상 (reward) 디자이너의 평가기준 ? 자원의 제한이 있을 때 ? Perfect knowledge, unlimited resources logical reasoning Imperfect knowledge, limited resources (limited) rationality Connection to economics, operational research, and control theory But ignores role of consciousness, emotions, fear of dying on intelligence
Introduction to AI12 Bits of History 1956: The name “Artificial Intelligence” was coined. (Would “computational rationality” have been better?) Early period (50’s to late 60’s): Basic principles and generality General problem solving Theorem proving Games Formal calculus
Introduction to AI13 Bits of History 1969-1971: Shakey the robot (Fikes, Hart, Nilsson) Logic-based planning (STRIPS) Motion planning (visibility graph) Inductive learning (PLANEX) Computer vision
Introduction to AI14 Bits of History Knowledge-is-Power period (late 60’s to mid 80’s): Focus on narrow tasks require expertise Encoding of expertise in rule form: If: the car has off-highway tires and 4-wheel drive and high ground clearance Then: the car can traverse difficult terrain (0.8) Knowledge engineering 5 th generation computer project CYC system (Lenat)
Introduction to AI15 Bits of History AI becomes an industry (80’s – present): Expert systems: Digital Equipment, Teknowledge, Intellicorp, Du Pont, oil industry, … Lisp machines: LMI, Symbolics, … Constraint programming: ILOG Robotics: Machine Intelligence Corporation, Adept, GMF (Fanuc), ABB, … Speech understanding
Introduction to AI16 Bits of History The return of neural networks, genetic algorithms, and artificial life (80’s – 90’s) Increased connection with economics, operational research, and control theory (90’s – present) AI becomes less philosophical, more technical and mathematically oriented
Introduction to AI17 Predictions and Reality … (1/3) In the 60’s, a famous AI professor from MIT said: “At the end of the summer, we will have developed an electronic eye” As of 2002, there is still no general computer vision system capable of understanding complex dynamic scenes But computer systems routinely perform road traffic monitoring, facial recognition, some medical image analysis, part inspection, etc…
Introduction to AI18 Predictions and Reality … (2/3) In 1958, Herbert Simon (CMU) predicted that within 10 years a computer would be Chess champion This prediction became true in 1998 Today, computers have won over world champions in several games, including Checkers, Othello, and Chess, but still do not do well in Go
Introduction to AI19 Predictions and Reality … (3/3) In the 70’s, many believed that computer-controlled robots would soon be everywhere from manufacturing plants to home Today, some industries (automobile, electronics) are highly robotized, but home robots are still a thing of the future But robots have rolled on Mars, others are performing brain and heart surgery, and humanoid robots are operational and available for rent (see: http://world.honda.com/news/2001/c011112.html)
Introduction to AI20 Mistakes … Often, the potential of a new field is over-estimated in its early age, but under-estimated over the longer term AI proponents have over-estimated the need for smart software, and under- estimated the feasibility and potential of large software systems based on massive coding effort
Introduction to AI21 생물학적으로 본 인간 인류의 진화 뇌의 크기 언어의 사용 도구의 사용 직립보행 사회생활 예측에 의한 행동 ?
Introduction to AI24 뇌의 진화과정 Sahelanthropus tchadensis 600 만 500 만 400 만 300 만 200 만 100 만 원인류 오스트랄로 피테쿠스 400-500 cc Homo habilus (handy man) 600-800 cc Homo erectus 800-1200 cc Homo sapiens 1300-1700 cc 뇌용적 : 유럽인 아프리카인 동아시아인 호주 원주민 네안데르탈 인
Introduction to AI31 Evolutionary leap. One of these primates is able to talk about what he's seeing; the other isn't. 'Speech Gene' Tied to Modern Humans FOXP2 gene - first identified by Monaco’s group at Oxford University (Science 2001) - 715 amino acids, two amino acid mutation in human lineage since 6 million years ago – fixed at 120,000 – 200,000 years ago (Svante Paabo, Nature 2002)
Introduction to AI35 Richard J. Davidson et al., Science 2000 ( 폭력과 전전두엽 장애 – 세로토닌 신경계 장애 ) 연쇄살인자 – 세로토닌 장애 – 책임문제 정신분열병 – 도파민 장애 – 살인 - 면죄부 폭력의 생물학
Introduction to AI36 전극의 전체 레이아웃 기록전극 부분의 확대도 생체 전자 공학 배양을 시작한 직후의 신경세포종의 모습배양 후 2 일이 경과한 신경세포종의 모습
Introduction to AI37 생체전자공학 뇌에 기계 또는 전자적 연결 눈 수술 귀 수술
Introduction to AI38 transgenic mice overexpressing the NR2B subunit of the NMDA receptor 뇌의 특정 유전자 과도 발현하는 형질 전환 마우스 제조 (smart mice) T. V. P. BLISS et al., Nature,1999
Introduction to AI39 최초의 유전자 치료술 ( 중증 복합 면역결핍증, SCID)
Introduction to AI40 Mistakes … Often, the potential of a new field is over-estimated in its early age, but under-estimated over the longer term What about Bio-informatics? 줄기세포의 치료효과 쥐의 실험에 의하면 척추장애를 완벽히 치료 그러나 저항력이 없는 쥐에서는 바로 암으로 전이, 있을 때에도 3 개월 뒤면 암으로 전이 ? 탄소 큐브 ( 나노기술 ) 완벽한 새로운 물질 인류는 경험하지 못했으며, 가장 무서운 발암물질 ? 핵, 유전자변형 ???
Introduction to AI41 Intelligent Agent 인간의 능력을 대신할 수 있는 부분적 : 걷는 ? 말하는 ? 판단하는 ? 인간과 같은 ? 지능적 능력을 가진 인간과 다른 형태의 ? 말하는 개 ? 말하는 앵무새 ? 덧셈을 하는 개 ? 비교 : SOAP, Service-oriented approach, XML, Context, …
Introduction to AI42 Notion of an Agent environment agent ? sensors actuators laser range finder sonars touch sensors
Introduction to AI43 Notion of an Agent environment agent ? sensors actuators
Introduction to AI44 Notion of an Agent environment agent ? sensors actuators Locality of sensors/actuators Imperfect modeling Time/resource constraints Sequential interaction Multi-agent worlds
Introduction to AI45 단순화한 인공지능 문제 에이전트의 조건 성공을 평가한 판단기준 환경 또는 응용영역에 대한 사전지식 Agent 가 행할 수 있는 행위 현재까지 한 행위와 결과에 대한 인식 문제의 어려움 Fully observable vs. Partially observable Deterministic vs. Stochastic Episodic vs. Sequential Static vs. Dynamic Discrete vs. Continuous Single agent vs. Multiagent
Introduction to AI46 Example: Tracking a Target target robot The robot must keep the target in view The target’s trajectory is not known in advance The robot may not know all the obstacles in advance Fast decision is required