Artificial Intelligence George Konidaris gdk@cs.brown.edu Fall - - PowerPoint PPT Presentation

▶
artificial intelligence
SMART_READER_LITE
LIVE PREVIEW

Artificial Intelligence George Konidaris gdk@cs.brown.edu Fall - - PowerPoint PPT Presentation

Nov 08, 2022 325 likes •998 views

Artificial Intelligence George Konidaris gdk@cs.brown.edu Fall 2019 1410 Team Instructor : George Konidaris Hours : Wed 4-5pm, CIT 447 HTAs: Leon Lei and Aansh Shah TAs : Alex Liu Jesus Contreras Ariel

slide-1
SLIDE 1

Artificial Intelligence

George Konidaris gdk@cs.brown.edu

Fall 2019

slide-2
SLIDE 2

1410 Team

Instructor: George Konidaris Hours: Wed 4-5pm, CIT 447 HTAs: Leon Lei and Aansh Shah TAs: Alex Liu Jesus Contreras Ariel Rotter-Aboyoun Kaiqi Kiang Berkan Hiziroglu Katie Scholl Chris Zamarripa Maulik Dang Daniel de Castro Megan Gessner Deniz Bayazit Nikhil Pant Elizabeth Zhao Roelle Thorpe Fawn Tong Spencer Greene Husam Salhab Troy Moo Penn

slide-3
SLIDE 3
slide-4
SLIDE 4

Major Topics Covered

slide-5
SLIDE 5

On Lectures

The textbook contains everything you need to know. Lectures contain everything you need to know. Lecture notes do not contain everything you need to know. Suggested approach:

  • Come to lectures and pay attention.
  • Revise via textbook (immediately).
  • Clarify at office hours.
slide-6
SLIDE 6

Required Text

Artificial Intelligence, A Modern Approach Russell & Norvig, 3rd Edition.

slide-7
SLIDE 7

Logistics

Course webpage: http://cs.brown.edu/courses/cs141/

  • Syllabus
  • Calendar - office hours!
  • Assignments etc.

Written assignments and grades etc. via Gradescope Comms (Q&A, announcements) via Piazza Make sure to sign up!

slide-8
SLIDE 8

Questions

Piazza: Quick question, or question many people may want to know the answer to. UTA Hours: Assignment and coding questions, material covered in lectures. GTA / Professor Hours: conceptual questions, or questions beyond the coursework.

slide-9
SLIDE 9

Grading

Exams:

  • Midterm: 15%, in class.
  • Final: 15%, finals week.
  • Closed book.

Six assignments

  • 50% of grade.
  • Python programming + report
  • Generally 1-2 weeks long
  • First assignment already available.

Extended project: 20%.

slide-10
SLIDE 10

Academic Honesty

I expect all Brown students to conduct themselves with the highest integrity, according to the Brown Academic Code. It is OK to:

  • Have high-level discussions.
  • Google for definitions and background.

It is NOT OK TO:

  • Hand in anyone else’s code, or work, in part or in whole.
  • Google for solutions.

ALWAYS HAND IN YOUR OWN WORK.

slide-11
SLIDE 11
slide-12
SLIDE 12

Academic Honesty

Consequences of cheating:

  • Your case will be reported.
  • Possible consequences include zeros on the assignment,

suspension, failure to graduate, retraction of job offers. If I catch you I will refer you to the Office of Student Conduct, and I will push for a hearing with the Standing Committee. DO NOT CHEAT.

slide-13
SLIDE 13

AI

slide-14
SLIDE 14

AI: The Very Idea

For as long as people have made machines, they have wondered whether machines could be made intelligent.

(pictures: Wikipedia)

slide-15
SLIDE 15
slide-16
SLIDE 16

(pictures: Wikipedia)

slide-17
SLIDE 17
slide-18
SLIDE 18

Turing

Computing machinery and

  • intelligence. Mind, October

1950. “Can machines think?”

(picture: Wikipedia)

slide-19
SLIDE 19

Dartmouth, 1956

slide-20
SLIDE 20

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Hinton

slide-21
SLIDE 21

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Hinton

slide-22
SLIDE 22

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I

Hinton

slide-23
SLIDE 23

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I

Hinton

slide-24
SLIDE 24

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI

Hinton

slide-25
SLIDE 25

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI

Hinton

slide-26
SLIDE 26

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI

Hinton

slide-27
SLIDE 27

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter

Hinton

slide-28
SLIDE 28

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter

Hinton

slide-29
SLIDE 29

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II

Hinton

slide-30
SLIDE 30

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II

Hinton

slide-31
SLIDE 31

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II Bayes

Hinton

slide-32
SLIDE 32

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II Bayes

Hinton

slide-33
SLIDE 33

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II Bayes

Hinton

slide-34
SLIDE 34

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II Bayes

Hinton

slide-35
SLIDE 35

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II Reinforcement Learning Bayes

Hinton

slide-36
SLIDE 36

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II Reinforcement Learning Bayes

Hinton

slide-37
SLIDE 37

Trends

1940 2020 1980 1960 2000 1990 2010 1970 1950

Connectionism I GOFAI AI Winter Connectionism II Reinforcement Learning Bayes

Hinton

Deep Learning (C III)

slide-38
SLIDE 38

Modern AI

Subject of intense study:

  • Nearly every CS department has at least 1 AI researcher.
  • ~ 700 PhDs a year in the US
  • Thousands of research papers written every year.
  • Heavily funded (NSF, DARPA, EU, etc.).
  • Pays itself back fast (e.g., DART).
  • Most major companies have efforts in this direction
  • Google,
  • Amazon
  • Microsoft, etc.
slide-39
SLIDE 39

Modern AI

(picture: Wikipedia)

slide-40
SLIDE 40

What is AI?

slide-41
SLIDE 41

Fundamental Assumption

The brain is a computer.

=

(picture: Wikipedia)

slide-42
SLIDE 42

What is AI?

This turns out to be a hard question! Two dimensions:

  • “Humanly” vs “Rationally”
  • “Thinking” vs. “Acting”.

thinking humanly thinking rationally acting humanly acting rationally

slide-43
SLIDE 43

What is AI?

thinking humanly thinking rationally acting humanly acting rationally

slide-44
SLIDE 44

What is AI?

thinking humanly thinking rationally acting humanly acting rationally cognitive science

slide-45
SLIDE 45

What is AI?

thinking humanly thinking rationally acting humanly acting rationally cognitive science “emulation”

slide-46
SLIDE 46

What is AI?

thinking humanly thinking rationally acting humanly acting rationally cognitive science “emulation” laws of thought

slide-47
SLIDE 47

What is AI?

thinking humanly thinking rationally acting humanly acting rationally cognitive science “emulation” laws of thought rational agents

slide-48
SLIDE 48

What is a Rational Agent?

sensors actuators

Performance measure.

slide-49
SLIDE 49

What is a Rational Agent?

sensors actuators

agent program Performance measure.

slide-50
SLIDE 50

Rational Agents

A rational agent:

  • acts in its environment
  • according to what is has perceived
  • in order to maximize
  • its expected performance measure.
slide-51
SLIDE 51

Rational Agents

A rational agent:

  • acts in its environment
  • according to what is has perceived
  • in order to maximize
  • its expected performance measure.

actuators

slide-52
SLIDE 52

Rational Agents

A rational agent:

  • acts in its environment
  • according to what is has perceived
  • in order to maximize
  • its expected performance measure.

actuators sensors

slide-53
SLIDE 53

Rational Agents

A rational agent:

  • acts in its environment
  • according to what is has perceived
  • in order to maximize
  • its expected performance measure.

actuators sensors agent program

slide-54
SLIDE 54

Rational Agents

A rational agent:

  • acts in its environment
  • according to what is has perceived
  • in order to maximize
  • its expected performance measure.

actuators sensors agent program given

slide-55
SLIDE 55

Example: Chess

Performance measure? Environment? Prior knowledge? Sensing? Actions?

(picture: Wikipedia)

slide-56
SLIDE 56

Chess

The chess environment is:

  • Fully observable.
  • Deterministic.
  • Episodic.
  • Static.
  • Discrete.
  • “Known”.

(picture: Wikipedia)

slide-57
SLIDE 57

Example: Mars Rover

Performance measure? Environment? Prior knowledge? Sensing? Actions?

(picture: Wikipedia)

slide-58
SLIDE 58

Mars Rover

The Mars Rover environment is:

  • Partially observable.
  • Stochastic.
  • Continuing.
  • Dynamic.
  • Continuous.
  • Partially known.
slide-59
SLIDE 59

Are We Making Progress?

Specific vs. General

slide-60
SLIDE 60

Progress

[Mnih et al., 2015]

video: Two Minute Papers

slide-61
SLIDE 61

Progress

[Mnih et al., 2015]

video: Two Minute Papers

slide-62
SLIDE 62

Atari

[Mnih et al., 2015]

slide-63
SLIDE 63

Structure of the Field

AI is fragmented:

  • Learning
  • Planning
  • Vision
  • Language
  • Robotics
  • Reasoning
  • Knowledge Representation
  • Search
slide-64
SLIDE 64

Progress

Progress in AI:

  • Clear, precise models of a class of problems
  • Powerful, general-purpose tools
  • A clear understanding of what each model and tool can

and cannot do

slide-65
SLIDE 65

Progress

Progress in AI:

  • Clear, precise models of a class of problems
  • Powerful, general-purpose tools
  • A clear understanding of what each model and tool can

and cannot do

  • Occasionally: vividly illustrative applications.
  • Arduous and slow
slide-66
SLIDE 66

Progress

Progress in AI:

  • Clear, precise models of a class of problems
  • Powerful, general-purpose tools
  • A clear understanding of what each model and tool can

and cannot do

  • Occasionally: vividly illustrative applications.
  • Arduous and slow
  • Huge opportunity