210 likes | 327 Views
Please pick up a copy of the course syllabus from the front desk. http://www.pami.uwaterloo.ca/~khoury/ece457. Introduction to AI. ECE457 Applied Artificial Intelligence Spring 2008 Lecture #1. Outline. What is an AI? Russell & Norvig, chapter 1 Agents Environments
E N D
Please pick up a copy of the course syllabus from the front desk. http://www.pami.uwaterloo.ca/~khoury/ece457 ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 1
Introduction to AI ECE457 Applied Artificial Intelligence Spring 2008 Lecture #1
Outline • What is an AI? • Russell & Norvig, chapter 1 • Agents • Environments • Russell & Norvig, chapter 2 ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 3
Artificial Intelligence • Computer players in video games • Robotics • Assembly-line robots, auto-pilot, Mars exploration robots, RoboCup, etc. • Expert systems • Medical diagnostics, business advice, technical help, etc. • Natural language • Spam filtering, translation, document summarization, etc. • Artificial intelligence is all around us ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 4
What is an AI? • Systems that… • Rationality vs. Humans: emotions, instincts, etc. • Thinking vs. acting: Turing test vs. Searle’s Chinese room • Engineers (and this course) focus mostly on rational systems ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 5
Act Rationally • Perceive the environment, and act so as to achieve one’s goal • Not necessary to do the best action • There’s not always an absolutely best action • There’s not always time to find the best action • An action that’s good enough can be acceptable • Example: Game playing • Sample approach: Tree-searching strategies • Problem: Choosing what to do given the constraints ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 6
Think Rationally • Use logic to reach a decision or goal via logical inference • Example: Theorem proving • Sample approach: First-order logic • Problems: • Informal knowledge • Uncertainty • Search space ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 7
Acting vs. Thinking Rationally • Both can lead to the same result • Acting rationally requires rational decision-making • Thinking rationally discovers the most rational action to do • So what’s the difference? • Acting rationally can be done without thinking • Thinking rationally can infer new information ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 8
Act Humanly • “Turing-test” AI • Improve human-machine interactions up to human-human level • Drawbacks: • In some cases, requires dumbing down the AI • Lots of man-made devices work well because they don’t imitate nature ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 9
Think Humanly • Cognitive science • Neural networks • Helps in other fields • Computer vision • Natural language processing ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 10
Rational Agents • An agent has • Sensors to perceive its environment • Actuators to act upon its environment • A rational agent has an agent program that allows it to do the right action given its precepts Environment Percepts Actions Sensors Actuators Agent Program ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 11
Types of Agents • Simple reflex agent • Selects action based only on current perception of the environment • Model-based agent • Keeps track of perception history • Goal-based agent • Considers what will happen given its actions • Utility-based agent • Adds the ability to choose between conflicting/uncertain goals • Learning agent • Adds the ability to learn from its experiences ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 12
Simple Reflex Agent Environment Percepts Actions Actuators Sensors Current State Selected Action If-then Rules ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 13
Simple Reflex Agent • Dune II (1992) units were simple reflex agents • Harvester rules: • IF at refinery AND not empty THEN empty • IF at refinery AND empty THEN go harvest • IF harvesting AND not full THEN continue harvesting • IF harvesting AND full THEN go to refinery • IF under attack by infantry THEN squash them ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 14
Model-Based Agent Environment Percepts Actions Actuators Sensors Current State Selected Action If-then Rules Previous perceptions World changes Impact of actions ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 15
Goal-Based Agent Environment Percepts Actions Actuators Sensors Current State State if I do action X Selected Action Previous perceptions World changes Goal Impact of actions ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 16
Utility-Based Agent Environment Percepts Actions Actuators Sensors Current State State if I do action X Happiness in that state Selected Action Previous perceptions World changes Utility Impact of actions ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 17
Learning Agent Environment Percepts Actions Actuators Sensors Performance Element Knowledge Changes Critic Learning Element Problem Generator Feedback Learning Goals Performance standard ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 18
Properties of the Environment • Fully observable vs. partially observable • See everything vs. hidden information • Chess vs. Stratego • Deterministic vs. stochastic vs. strategic • Controlled by agent vs. randomness vs. multiagents • Sudoku vs. Yahtzee vs. chess • Episodic vs. sequential • Independent episodes vs. series of events • Face recognition vs. chess ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 19
Properties of the Environment • Static vs. dynamic vs. semi-dynamic • World waits for agent vs. world goes on without agent vs. world waits but agent timed • Translation vs. driving vs. chess with timer • Discrete vs. continuous • Finite distinct states vs. uninterrupted sequence • Chess vs. driving • Single agent vs. cooperative vs. competitive • Alone vs. team-mates vs. opponents • Sudoku vs. sport team vs. chess ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 20
Properties of the Environment • Crossword Puzzle • Fully observable, deterministic, sequential, static, discrete, single-agent • Monopoly • Fully observable, stochastic, sequential, static, discrete, competitive multi-agent • Driving a car in the real world • Partially observable, stochastic, sequential, dynamic, continuous, cooperative multi-agent • Assembly-line inspection robot • Fully observable, deterministic, episodic, dynamic, continuous, single-agent ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 21