Вы находитесь на странице: 1из 66

CS 510: Intro to Articial Intelligence

Rachel Greenstadt Department of Computer Science Drexel University www.cs.drexel.edu/~greenie/cs510/index.html

Overview
What is Articial Intelligence? History of AI What is CS 510? Syllabus, Schedule, Grading Final Project Overview of AI Topics

Introductions
Introduce yourself:

Your name Undergrad/Masters/Ph.D/How many years at Drexel? What is your research area? Which faculty member(s) do you work with? What brings you to CS 510? What else should we know about you? :)

What is AI?

Class Exercise
Answer the following questions on three
index cards: What is Intelligence? What is Articial Intelligence? What is an agent? What attributes does an agent have? a neighbor

When youre done, swap your answers with

Each card has a number or letter on one side and a square or circle on the other side

42

Which cards must you turn over to determine if the following statement is true: Every card with a letter on one side has a square on the other side

Thinking like humans


90% of humans get it wrong Answer is cards 2 and 3 Most people pick 1 and 3

Each card has an age on one side and a drink on the other side

20 yrs

24 yrs

Beer Cola

Which cards must you turn over to determine if the following statement is true: Everyone in the bar is following the law.

What is AI?
Thinking like a human Thinking rationally

Acting like a human

Acting rationally

Why Study AI?


Fundamental scientic questions What does it mean to be smart? What makes us smart? Can our intelligence be replicated or
exceeded? And how?

Why Study AI?


Fundamentally useful engineering question AI in computers increases humanitys
collective intelligence and abilities to act rationally limit us

Areas where computers lack the ability

But is it even possible?


Billions of human computers must be doing
something....

Strong vs. Weak AI Human-level intelligent machines,


conscious?

thinking-like features to make


computers more useful

agent

1. One that acts or has the power or authority to acts 2. One empowered to act for or represent another

13

Agents

Simple reex agent

Modern AI Agents

Not just AI, but AI situated in some environment Not just inference, but inference used in some context Not just a control loop, but complex autonomous decision-making Not just an algorithm, but an intelligent system Holistic approach to AI Multiple AI tools can be integrated to build an Agent

Intelligent Software Agents

Responsive Goal-Directed Autonomous Social


17

PEAS
Performance Measure Environment Actuators Sensors Examples?

Autonomous Cars

Consider an automated taxi driver:

Performance measure: Safe, fast, comfortable trip, maximize prots Environment: Roads, other trafc, pedestrians, customers Actuators: Steering wheel, accelerator, brake, signal, horn Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard, lidar

Agent or Program?

The easy stuff is hard


Computers still cant speak, see, or reason
like a 5 year old child

And the hard stuff is easy.... Playing chess Proving theorems Diagnosing medical conditions

AI Historical Highlights

5th century

Aristotle invents syllogistic logic zairja device used by Arab astrologers to calculate ideas mechanically Ramon Llull creates Ars Magna theological argumentation device Material arguments for thinking: Hobbes, Descartes Pascal invents mechanical calculating device Babbage and Lovelace work on programmable mechanical machine Boolean algebra representing some laws of thought

13th century

17th century

19th century

AI Historical Highlights

1928 von Neumans minimax algorithm, used for game-playing 1950 Turing test devised 1950 Asimov publishes the 3 laws of robotics 1956 McCarthy coins Articial Intelligence / Dartmouth conference Early years (1956-1970)

Micro-worlds Reasoning by search Many successes, lots of optimism/hype - Samuels checkers, Gelemters Geometry theorem prover, Shakey, Dendral

AI Historical Highlights

AI Winter (1970s)

Perceptrons - limits of neural networks language difculties - The spirit is willing but the esh is weak ==> The vodka is good but the meat is rotten Development of computational complexity Loss of funding

AI becomes an industry (1980s) Expert, intelligent systems all the rage Bubble happens and expectations raised again

AI Historical Highlights

2nd AI Winter (late 1980s - 1990s)

More disappointment as AI fails to make people rich Expert systems are brittle Funding cut again

AI Becomes a Science/Intelligent Agents (1987-present) Victory of the neats (vs scrufes) Statistical machine learning/HMMs has many successes AI starts to make people rich Moores law makes a lot more possible Emergence of Intelligent Agent approach Availability of very large data sets

AI State of the Art

AI Applications

AI in Space
Exploring Mars Autonomous satellite separation and docking Monitoring the sky with telescope arrays

AI Art

What is CS 510?

Course Information

Textbook

Stuart Russell and Peter Norvig Articial Intelligence: A Modern Approach

Prentice-Hall (Third Edition)

Supplementary Readings Available on course website http://www.cs.drexel.edu/~greenie/cs510.html

Course Objectives
Learn about AI techniques Learn how to do AI research (grad class)

Schedule
Intro to AI Search and Problem Solving Planning Knowledge Representation Learning

Evaluation
30% Exams Midterm 15% Final 15% 5% Machine Learning exercise 25% Class Participation 40% Final Project

Class Participation
In class exercises Class discussions bbvista Online discussions More instructions on website

Facilitation

Each person will be responsible for leading a short discussion around one topic/paper

Discussion should involve either :

A 5-10 minute presentation/demo on related material

Related paper, background, application

A summary/highlights reel of the online discussion

Rest should be class discussion/exercises led by you

Topics

the ai enterprise (Turing) 09/29 multiagent systems (Sycara) 09/29 search - google (Page, et al) 10/6 search - dynamic environments (Koenig and Likhachev) 10/13 constraint reasoning (RN Ch 6) 10/13 games (Billings et al (poker)) 10/27 game theory (Mechanism Design) 10/27

logic/knowledge representation (RN Ch 7-8, BDI) 11/3 teamwork/joint intention (Cohen and Levesque) 11/3 planning (RN Ch 11) 11/10 distributed planning 11/10 machine learning (general) 11/17 machine learning (adversarial classication) 11/17 Reinforcement learning 11/24 NLP 11/24

Final Project Read Handout!


Free form research project Groups of 1-3 people Milestones

Reviewer comments due (Oct 8) Proposal due (Oct 13) Reviewer discussion notes due (Nov 10) Presentation (Dec 1) Project write up (Dec 1) Review due (Dec 4)

Groups and topic (Sept 29) Proposal draft sent to reviewer (Oct 6)

The Final Project Proposal


2 pages long Problem Statement and Motivation Brief Description of Approach Related Work and novelty Evaluation approach Milestones

Peer Review
Each of you will be assigned another group
to shepherd through the project process the other project

Goal is to provide constructive feedback on At week 3 (project proposal draft) At week 7 (project progress) At week 10 (nal paper)

AI Topics

Search
The Heuristic Search Hypothesis Subroutine of intelligent systems

problem solving planning knowledge games

(Newell and Simon)

Some search issues well discuss


Intractability of exhaustive search Use of heuristics (A*) Local search satiscing

Open Problems
Distributed search Dynamic search Check out STAIRS workshop

Last year:
A Travel-Time Optimizing Edge Weighting Scheme for Dynamic Re-planning.! Andrew Feit, Lenrik Toval, Raf Hovagimian and Rachel Greenstadt. AAAI 2010 Workshop on Bridging The Gap Between Task And Motion Planning (BTAMP) http://www.seas.upenn.edu/~maximl/wt/AAAI10_ws/BTAMP10_schedule.html

Constraint Reasoning

Way of representing knowledge and structure on a problem so that standard heuristics can be applied Problems expressed as:

Set of variables that need values Set of domains from which the values are drawn Set of constraints that represent relationships between the variables (must be satised or optimized)

Applications
Supply chain management Scheduling Resource and task allocation Multiagent coordination

Open problems in Constraint Reasoning



How to easily express problems as constraint problems What if the domain is dynamic or uncertain? How do you measure performance in distributed systems? See the Constraint Programming (CP) conference or the Distributed Constraint Reasoning (DCR) workshop I do research in Distributed Constraint Reasoning (as does Evan Sultanik, the other section designer), we can work with you to come up with a topic in this area if you want

Games / Adversarial Search



Inherently multiagent and competitive Classic work in turn based games

Chess Checkers Now poker, general game playing

http://www.computerpokercompetition.org/ http://games.stanford.edu/

Mechanism Design

Construct incentives for agents that are:

self-interested utility-maximizing Auctions Reputation systems Trafc systems

Applications

Knowledge Representation
What is common sense? How a problem is represented greatly affects its efciency How can we encode the things we know so computers understand them? Links

http://openmind.media.mit.edu/ http://rtw.ml.cmu.edu/rtw/

Model-based Reex Agent

Planning

Given

a set of actions a goal state a present state

Choose actions to get to the goal state And what if you have a team of agents...

Goal-based Agent

Utility-based Agent

Planning problems
Planning in the real world Highly dynamic environments Uncertain information

Learning
What does it mean for computers to learn? Supervised Unsupervised

Learning
What does it mean for computers to learn? Supervised
circle square circle square

Unsupervised

Learning
What does it mean for computers to learn? Supervised
circle square circle square

Unsupervised

Learning
What does it mean for computers to learn? Supervised
circle square circle square

Unsupervised
group these into two categories

Learning Agent

Learning Projects
Predicting community ratings on web
forums and blogs

Authorship recognition learning who wrote a document by


linguistic style

We have applied this to slashdot.org

Experiment with applying to text

messages/twitter/transcribed speech

Topics

the ai enterprise (Turing) 09/29 multiagent systems (Sycara) 09/29 search - google (Page, et al) 10/6 search - dynamic environments (Stentz) 10/13 constraint reasoning (RN Ch 5) 10/13 games (Billings et al (poker)) 10/27 game theory (Mechanism Design) 10/27

logic/knowledge representation (RN Ch 7-8, BDI) 11/3 teamwork/joint intention (Cohen and Levesque) 11/3 planning (RN Ch 11) 11/10 distributed planning 11/10 machine learning (general) 11/17 machine learning (adversarial classication) 11/17 reinforcement learning 11/24 ai and the brain 11/24

Project starting points



psal.cs.drexel.edu

Current research by my research group

Robocup soccer http://www.robocup.org

Search and rescue http://www.robocuprescue.org http://maple.cs.umbc.edu/~ericeaton/searchandrescue/

Animated lifelike agents http://hmi.ewi.utwente.nl/gala

Project starting points



The JavaFF planner

http://personal.cis.strath.ac.uk/~ac/JavaFF/

Sports prediction markets http://www.facebook.com/apps/application.php?id=8575690818

Games http://www.cs.ualberta.ca/~games/

Electronic markets http://www.sics.se/tac/page.php?id=1

Resources
http://www.aaai.org/AITopics http://aima.cs.berkeley.edu http://library.drexel.edu http://aispace.org

Readings this week:

Turing, A.M. (1950). Computing machinery and intelligence. Mind, 59, 433-460. Katia Sycara, Multiagent Systems, AI Magazine 19(2): Summer 1998, 79-92.

Оценить