Ch1 AI intro kho tài liệu bách khoa

What is AI (Artificial Intelligence) 3/15/2016 Topics • Quotes & Concepts • Goals & Approaches • Application Areas • Framework for AI Systems • Fundamental Issues for AI Problems 3/15/2016 What is AI? “It is the science and engineering of making intelligent machines, especially intelligent computer programs It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable.” “Intelligence is the computational part of the ability to achieve goals in the world.” J McCarthy 3/15/2016 What is AI? “AI is the design, study and construction of computer programs that behave intelligently.” Tom Dean 3/15/2016 What is AI? “AI is the study of complex information processing problems that often have their roots in some aspect of biological information processing The goal of the subject is to identify solvable and interesting information processing problems, and solve them.” David Marr (1945-1980) 3/15/2016 What is intelligent behavior? • Perceiving one’s environment • Acting in complex environments • Learning and understanding from experience • Using reasoning to solve problems and to discover “hidden” knowledge • Applying knowledge successfully in new situations • Thinking abstractly, using analogies • Communicating with others 3/15/2016 Goals of AI • To replicate human intelligence (still distant goal) • To solve knowledge-intensive tasks • To make an intelligent connection between perception and action • To enhance human-human, human-computer and computer-computer interaction/communication – Computer can sense and recognize its users, see and recognize its environment, respond visually and audibly to stimuli – New paradigms for interacting productively with computers using speech, vision, natural language, 3D virtual reality,… 3/15/2016 Goals of AI • Engineering Goal – Develop concepts, theory and practice of building intelligent machines – Emphasis on system building • Science Goal – Develop concepts, mechanisms and vocabulary to understand biological intelligent behavior – Emphasis on understanding intelligent behavior 3/15/2016 Approaches to AI • Choose – The goals of the computational model – The basis for evaluating performance of the system Human-like: Think: 1) Think like humans Cognitive science Act: 3/15/2016 Rational: 2) Think rationally Laws of thought 3) Act like humans 4) Act rationally Behaviorist approach Satisficing methods Goals of and Approaches to AI • Box 1: Cognitive Science Approach – Focus on behavior and I/O – Model reasoning processes – Computational model should reflect how results were obtained • Goal – Not just to produce human like behavior (box 3) but to produce a reasoning process similar to the steps used by humans 3/15/2016 10 AI Apps Top-10 List Language translation services (Google) News aggregation and summarization (Google) Speech recognition (Nuance) Song recognition (Shazam) Face recognition (Recognizr) Image recognition (Google Goggles) Question answering (Apple Siri, IBM Watson) Chess playing (IBM Deep Blue) 3D scene modeling from images (Microsoft Photosynth) 10 Driverless cars (Google) 3/15/2016 22 Some AI "Grand Challenge" Problems • Intelligent Agents • Smart Clothes • Aids for the Disabled • Tutors • Accident-Avoiding Vehicles • Self-Organizing Systems • Translating Telephone Conversations • Extracting and representing information from lots of data – Neural networks, hidden Markov models, – Bayesian networks, heuristic search, logic, … 3/15/2016 23 A Framework for Building AI Systems • Perception • Reasoning • Action 3/15/2016 24 Perception • Biological systems experience the world through their senses • What perceptions would be needed by: – autonomous vehicle? camera images and range data – medical diagnosis system? symptoms and test results • Includes areas of – – – – vision speech processing natural language processing signal processing, eg: market data, acoustic data 3/15/2016 25 Reasoning • Includes inferencing, decision-making, classifying from what is sensed and state of internal "model" of the world • AI systems use: – – – – – – heuristic search in a problem space logical deduction system neural networks genetic algorithms hidden Markov model induction Bayes network inferencing 3/15/2016 26 Reasoning (cont) • Includes areas of: – – – – – – – knowledge representation problem solving decision theory planning game theory machine learning uncertainty reasoning 3/15/2016 27 Action • Biological systems interact with the world through their movements, sounds, other behaviors • What actions are needed by: – autonomous vehicle? steering and speed control, sensor positioning, … – medical diagnosis system? make prescriptions, suggest further tests, … • Includes areas of: – – – – – robot actuation natural language generation speech synthesis computer graphics sound synthesis 3/15/2016 28 Fundamental Issues for AI Problems • Representation • Search • Inference • Learning • Planning 3/15/2016 29 Representation • Facts about the world are remembered – – – – – – How we represent facts? What should we store? How we structure this knowledge? What is explicit? What is inferred? How are inference rules encoded? How should inconsistent, incomplete, and probabilistic knowledge be dealt with? 3/15/2016 30 Representation • Example: – "The fly buzzed irritatingly on the window pane Jill quickly picked up a newspaper." • What is the inference? – Jill is going to start a fire? – Jill is going to start a papiermache project? – Jill is going to exterminate the fly? 3/15/2016 31 Representation • Example: "Given 12 sticks in a by grid, move to leave exactly boxes." 3/15/2016 32 Search • A problem space is searched for a solution Checkers: 1040 states Chess: 10120 states – How limit the search space? – How we find an optimal solution? – How are heuristics and constraints used? 3/15/2016 33 Inference • New facts are determined from a set of existing facts – deduction – abduction non-monotonic reasoning – reasoning under uncertainty • Example: – All elephants have trunks Clyde is an elephant – Does Clyde have a trunk? – Willy has a trunk Is Willy an elephant? 3/15/2016 34 Learning • New knowledge is acquired – – – – – inductive inference neural networks genetic algorithms artificial life evolutionary approaches 3/15/2016 35 Planning • A strategy for achieving a goal in terms of a sequence of primitive actions is generated – – – – – What general facts about the world are needed? What facts about the specific situation are needed? What facts are needed about the effects of actions? How you state the goal? How you know the goal has been reached? 3/15/2016 36 ... world.” J McCarthy 3/15/2016 What is AI? AI is the design, study and construction of computer programs that behave intelligently.” Tom Dean 3/15/2016 What is AI? AI is the study of complex information... Concepts • Goals & Approaches • Application Areas • Framework for AI Systems • Fundamental Issues for AI Problems 3/15/2016 What is AI? “It is the science and engineering of making intelligent machines,... rational and sufficient 3/15/2016 13 Goals of and Approaches to AI • There are two kinds of people in the AI world: – Classical AI, the symbol-processing approach • Top down, knowledge to symbol