Rachel Greenstadt Department of Computer Science Drexel

CS 510: Intro to
Artificial Intelligence
Rachel Greenstadt
Department of Computer Science
Drexel University
www.cs.drexel.edu/~greenie/cs510/index.html
Overview
• What is Artificial 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 Artificial Intelligence?
• What is an agent? What attributes does an agent have?
• When you’re done, swap your answers with
a neighbor
Each card has a number or letter on one side
and a square or circle on the other side
A
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 scientific 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 humanity’s
collective intelligence and abilities
• Areas where computers lack the ability
to act rationally limit us
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 reflex 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 profits
Environment: Roads, other traffic, 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 can’t 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
13th century
•
•
zairja device used by Arab astrologers to calculate ideas mechanically
Ramon Llull creates Ars Magna theological argumentation device
17th century
•
•
Material arguments for thinking: Hobbes, Descartes
Pascal invents mechanical calculating device
19th century
•
•
Babbage and Lovelace work on programmable mechanical machine
Boolean algebra representing some “laws of thought”
AI Historical Highlights
•
•
•
•
•
1928 von Neuman’s minimax algorithm, used for game-playing
1950 Turing test devised
1950 Asimov publishes the 3 laws of robotics
1956 McCarthy coins “Artificial Intelligence” / Dartmouth conference
Early years (1956-1970)
•
•
•
Micro-worlds
Reasoning by search
Many successes, lots of optimism/hype - Samuel’s checkers, Gelemter’s
Geometry theorem prover, Shakey, Dendral
AI Historical Highlights
•
•
AI Winter (1970s)
•
•
Perceptrons - limits of neural networks
•
•
Development of computational complexity
language difficulties - “The spirit is willing but the flesh is weak” ==>
“The vodka is good but the meat is rotten”
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 “scruffies”)
Statistical machine learning/HMMs has many successes
AI starts to make people rich
Moore’s 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
Artificial 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
logic/knowledge representation
(RN Ch 7-8, BDI) 11/3
•
•
•
search - google (Page, et al) 10/6
teamwork/joint intention (Cohen
and Levesque) 11/3
planning (RN Ch 11) 11/10
•
constraint reasoning (RN Ch 6)
10/13
•
•
•
•
•
•
Reinforcement learning 11/24
•
•
search - dynamic environments
(Koenig and Likhachev) 10/13
games (Billings et al (poker))
10/27
game theory (Mechanism
Design) 10/27
distributed planning 11/10
machine learning (general) 11/17
machine learning (adversarial
classification) 11/17
NLP 11/24
•
•
•
Final Project
Read Handout!
Free form research
project
Groups of 1-3 people
Milestones
•
Groups and topic (Sept 29)
•
Proposal draft sent to
reviewer (Oct 6)
•
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)
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
• Goal is to provide constructive feedback on
the other project
• At week 3 (project proposal draft)
• At week 7 (project progress)
• At week 10 (final paper)
AI Topics
Search
• The “Heuristic Search Hypothesis”
-
(Newell and Simon)
• Subroutine of intelligent systems
•
•
•
•
problem solving
planning
knowledge
games
Some search issues
we’ll discuss
• Intractability of exhaustive search
• Use of heuristics (A*)
• Local search “satisficing”
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, Raffi 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 satisfied 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
•
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
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
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
Applications
•
•
•
Auctions
Reputation systems
Traffic systems
Knowledge
Representation
•
•
What is common sense?
•
How can we encode the things we know so
computers understand them?
•
Links
How a problem is represented greatly affects its
efficiency
•
•
http://openmind.media.mit.edu/
http://rtw.ml.cmu.edu/rtw/
Model-based Reflex
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
• We have applied this to slashdot.org
• Authorship recognition
• learning who wrote a document by
linguistic style
• Experiment with applying to text
messages/twitter/transcribed speech
Topics
•
•
the ai enterprise (Turing) 09/29
•
multiagent systems (Sycara)
09/29
logic/knowledge representation
(RN Ch 7-8, BDI) 11/3
•
•
•
search - google (Page, et al) 10/6
teamwork/joint intention (Cohen
and Levesque) 11/3
planning (RN Ch 11) 11/10
•
constraint reasoning (RN Ch 5)
10/13
•
•
•
•
•
•
reinforcement learning 11/24
•
•
search - dynamic environments
(Stentz) 10/13
games (Billings et al (poker))
10/27
game theory (Mechanism
Design) 10/27
distributed planning 11/10
machine learning (general) 11/17
machine learning (adversarial
classification) 11/17
ai and the brain 11/24
Project starting points
•
psal.cs.drexel.edu
•
•
Robocup soccer
•
•
http://www.robocup.org
Search and rescue
•
•
•
Current research by my research group
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
•
•
Sports prediction markets
•
•
http://www.facebook.com/apps/application.php?id=8575690818
Games
•
•
http://personal.cis.strath.ac.uk/~ac/JavaFF/
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.