please pick up a copy of the course syllabus from the front desk

21
ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 1 Please pick up a copy of the course syllabus from the front desk. http://www.pami.uwaterloo.ca/ ~khoury/ece457

Upload: columbia-adriel

Post on 02-Jan-2016

19 views

Category:

Documents


2 download

DESCRIPTION

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 - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 1

Please pick up a copy of the course syllabus from the front desk.

http://www.pami.uwaterloo.ca/~khoury/ece457

Page 2: Please pick up a copy of the course syllabus from the front desk

Introduction to AI

ECE457 Applied Artificial IntelligenceSpring 2008Lecture #1

Page 3: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 3

Outline What is an AI?

Russell & Norvig, chapter 1 Agents Environments

Russell & Norvig, chapter 2

Page 4: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 4

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

Page 5: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 5

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

Humanly Rationally

Think Neural networks

Theorem proving

Act ELIZA Deep Blue

Page 6: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 6

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

Page 7: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 7

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

Page 8: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 8

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

Page 9: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 9

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

Page 10: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 10

Think Humanly Cognitive science Neural networks Helps in other fields

Computer vision Natural language processing

Page 11: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 11

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

Perce

pts A

ction

s

Sensors

Actuators

Agent Progra

m

Page 12: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 12

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

Page 13: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 13

Simple Reflex Agent

EnvironmentPercepts

Actions

Sensors

Actuators

Selected

Action

Current State

If-then Rules

Page 14: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 14

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

Page 15: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 15

Model-Based Agent

EnvironmentPercepts

Actions

Sensors

Actuators

Selected

Action

Current State

Previous perceptio

nsImpact of actions

World changes

If-then Rules

Page 16: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 16

Goal-Based Agent

EnvironmentPercepts

Actions

Sensors

Actuators

Selected

Action

Current State

GoalPrevious perceptio

nsImpact of actions

World changes

State if I do action

X

Page 17: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 17

Utility-Based Agent

EnvironmentPercepts

Actions

Sensors

Actuators

Selected

Action

Current State

UtilityPrevious perceptio

nsImpact of actions

World changes

State if I do action

X

Happiness in that state

Page 18: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 18

Learning Agent

EnvironmentPercepts

Actions

Sensors

Actuators

Problem Generat

or

Learning

Element

Feedback

Performance standard

ChangesKnowledge

Learning Goals

Performance Element

Critic

Page 19: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 19

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

Page 20: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 20

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

Page 21: Please pick up a copy of the course syllabus from the front desk

ECE457 Applied Artificial Intelligence R. Khoury (2008) Page 21

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

Properties of the Environment