CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

23
CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin http://pages.cs.wisc.edu/~shavlik/ cs540.html

Transcript of CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

Page 1: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 – Introduction to AIFall 2015

Jude ShavlikTA: Dmitry Basavin

http://pages.cs.wisc.edu/~shavlik/cs540.html

Page 2: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 2

Today’s Topics• Administrivia

– The Class Home Page– Moodle Piazza?– Java, Eclipse IDE, and CS 367– Course Textbook (read Ch 1 and 2, Sec 18.1-18.3, Appendices A & B)– Missing class, late HWs, exam dates? TA Office Hours @ Epic?– A little about me …– Do not email me at [email protected]

(use [email protected])– Three 50-min lectures in 170 minutes

• Class Style• Some AI History and Philosophy• Machine Learning (in Lecture 2, Week 1)

• For next week: Read the Algorithm section of the Wikipedia page on Random Forests

and Pedro Domingos' paper A Few Useful Things to Know About Machine Learning (you can

access this paper for free if you are on a UW-Madison network; if you use DoIT's VPN

I believe you can also access this from a non-UW network, such as a computer in your home)

9/8/15

Page 3: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

Lecture 1, Slide 3

AI Magic

• Often mathematically complex algorithms• But lots of data (“big data”) and simple(r)

methods can work quite well!• Counting lots of things can lead to

intelligent behavior (HW4)• Arguably AI, especially machine learning

(ML), most important IT technology currently – still quite exciting after being it in for 30+ years!

9/8/15 CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1

Page 4: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 4

Class Style

• More about engineering intelligent s/w than modeling human cognition

• Concrete focus, to provide context for general AI ideas

• “Hands on” – learn more by (actively) doing than (passively) listening

• Try to write some notes during class, even though Powerpoint and videos of lectures available (more later)

9/8/15

Page 5: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 5

Work Load

• About five HWs (35% of grade), two with substantial programming

• Midterm (30%) – a Thursday evening?

• Final (35%) – Thursday evening Dec 17?

• Will grade more like a grad class than a ugrad class because you all have ugrad degrees

• I will teach more than I can test; don’t just focus on what is graded!

9/8/15

Page 6: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 6

You Remember (Metcalf, 1997 and others)

• 10% of what you read  

• 20% of what you hear  

• 30% of what you see  

• 50% of what you hear and see together  

• 70% of what you think and say out loud  

• 90% of what you do

• ??% of what you hear, see, and write down

9/8/15

Page 7: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 7

Programming Knowledge Assumed

• For loops, arrays, scanners (to read in data)

• Object-oriented design (eg, trees)

• Stacks, queues, linked lists, hash tables

• Recursion (see “Programming Knowledge Assumed” slide)

• Trees and recursion (cs 367 topics) will be a big part of HW1

• Math: partial derivatives (for neural nets); mathematical logic and prob covered in class

9/8/15

Page 8: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 8

HW Schedule (tentative)

HW0 – due next class, read in dataset for ML

HW1 – learn decision trees (Java)

HW2 – tune sets (Java), ensembles (Java), searching

for solutions (paper-and-pencil)

Midterm

HW3 – probabilistic reasoning (Java) and

case-based reasoning (paper-and-pencil)

HW4 – artificial neural networks and support vector

machines (paper-and-pencil)

HW5 – logical rep & reasoning (paper-and-pencil)

Final9/8/15

Page 9: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 9

Detailed List of Course TopicsLearning from labeled data

Experimental methodologies for choosing parameter settings and estimating future accuracy

Decision trees and random forests

Probabilistic models, nearest-neighbor methods

Genetic algorithms

Neural networks

Support vector machines

Reinforcement learning (if time permits)

Searching for solutions

Heuristically finding shortest paths

Algorithms for playing games like chess

Simulated annealing

Genetic algorithms

Reasoning probabilistically

Probabilistic inference

Bayes' rule

Bayesian networks 

9/8/15

Reasoning from concrete cases

Cased-based reasoning

Nearest-neighbor algorithm

Reasoning logically

First-order predicate calculus

Representing domain knowledge using mathematical logic

Logical inference

Problem-solving methods based on the biophysical world

Genetic algorithms

Simulated annealing

Neural networks

Philosophical aspects

Turing test

Searle's Chinese Room thought experiment

The coming singularity

Strong vs. weak AI

Societal impact of AI

Page 10: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 10

Late HW's Policy

• HW's due on-line in Moodle @ 11:55pm

• You have 5 late days to use over the semester

(Fri 11:55pm → Mon 11:55pm is 1 late "day")

• SAVE UP late days!

• Penalty points after late days exhausted

• Can't be more than ONE WEEK late so solutions can be posted

• Since this is a class for working professionals, we’ll be a bit more flexible wrt work travel

9/8/15

Page 11: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

9/8/15 CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 11

Academic Misconduct (also on course homepage)

All examinations, programming assignments, and written homeworks must be done individually. Cheating and plagiarism will be dealt with in accordance with University procedures (see the Academic Misconduct Guide for Students). Hence, for example, code for programming assignments must not be developed in groups, nor should code be shared. You are encouraged to discuss with your peers, the TAs or the instructor ideas, approaches and techniques broadly, but not at a level of detail where specific implementation issues are described by anyone. If you have any questions on this, please ask the instructor before you act.

Page 12: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 12

Some AI Milestones

• Computer beats leading chess grand master (1997)

• Computer wins Jeopardy (2011)

• Speech recognition in smartphone (2011)

• Self-driving cars (2014)

• “Star Trek telephone” (2015)

9/8/15

Page 13: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 13

The “Star Trek” Telephone

9/8/15

Machine Translation

Speech Generation

Speech Recognition

Japanese

English

Page 14: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 14

CS 540 at the Movies(suggest better/other videos)

• AI Algo Beats Kasparov at Chesshttps://www.youtube.com/watch?v=NJarxpYyoFI

• IBM Watson Wins Jeopardyhttps://www.youtube.com/watch?v=WFR3lOm_xhE

• Stanford+Google Car http://www.ted.com/talks/sebastian_thrun_google_s_driverless_car

• Microsoft SKYPE Translatorhttps://www.youtube.com/watch?v=mWTySUGXR2k&list=PLD7HFcN7LXRd4kd2XgZjIbQ8TwTC32Zc9&index=3

• CS 540 Nannon© Competitionhttps://www.youtube.com/watch?v=b1SqrjuPrmE9/8/15

Page 15: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 15

DARPA Grand Challenge (2005)

• Oshkosh Truck came in 5th

• 4th: a Louisiana insurance company!

– Story about searching for best path through dried lake bed …

– Many fine paths, too much time spent thinking!

• What is the key difference between Chessand Jeopardy/Car-Driving?

– ‘closed’ vs. ‘open’ world

• Can you write a progam that is smarter than you?

– You likely will in cs5409/8/15

Page 16: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

Lecture 1, Slide 16

Some More Videos/Images

• Robots Falling Down at the 2015 DARPA Robotics Challenge https://www.youtube.com/watch?v=g0TaYhjpOfo

• Google Translate (2015 cellphone app)

9/8/15

Page 17: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 17

In which Year will Children Born that Year not Need to Learn How to Drive?

Recently a leading robotics researcher said his answer is ‘2014’

• Robots too polite? Eg, never speed, always yield

• Will existing cars be retrofitted?

• Will airplanes (especially freight) and trucks be first?

9/8/15

Page 18: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 18

Machine Learning is Becoming Ubiquitous

• Search (in the Google/Bing/etc sense)

• Credit-card scoring, finance in general

– Why might “hadBankruptcy” be the best feature for deciding who gets a credit card?

• Personalization/recommendation in various forms

• Extracting ‘knowledge’ from ‘natural’ languages (Machine Reading)

• Understanding pictures and videos, face recognition

• ML large focus of CS 540(overlap with CS 760, grad ML class)

9/8/15

Page 19: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 19

An AI Axiom

The easier something is for humans the harder it is for computers

And vice versa

• A point I’ve been making for 25 years,but maybe no longer true?

• Human-machine cooperation appealing

• AI (rapidly) replacing ‘white collar’ jobs? (Robots have been replacing ‘blue collar’ jobs for awhile)

9/8/15

Page 20: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 20

The Coming Singularity?

9/8/15

Page 21: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 21

Some Interesting Quotes

• “Machine intelligence is the last invention that humanity will ever need to make.”http://www.ted.com/talks/nick_bostrom_what_happens_when_our_computers_get_smarter_than_we_are

• “When thinking about the future we tend to over estimate the impacts in the near-term and under estimate impacts in the long term.” Roy Amara, Institute for the Future (http://www.iftf.org/home/)

9/8/15

Page 22: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 22

Linear Thinking

Time into the FuturePre

dict

ed A

mou

nt o

f Cha

nge

How we tend to predict the future

How technology actually advances

9/8/15

Page 23: CS 540 – Introduction to AI Fall 2015 Jude Shavlik TA: Dmitry Basavin shavlik/cs540.html.

CS 540 - Fall 2015 (Shavlik©), Lecture 1, Week 1 Lecture 1, Slide 23

More AI Philosophy in Final Class this Term

• Turing Test

• Searle’s Chinese Room story

• Weak and Strong AI hypotheses

• The future of AI including its societal impact

• Additional AI classes at Wisconsin

9/8/15