5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu...

19
v=1 v=–1 v=–1 v=–1 v=–1 v=1 optima O O O X X O O O X X X X O O O X X X X O O O X X X X O OO X X X O O O X X X O O O O O X X X X O X O X O O X 2) 3) 5) 6) 7) 8) 9) 12) O O O O X X X X O 11) O O O O X X X O X O 13) O O INTRODUCTION TO ARTIFICIAL INTELLIGENCE DATA15001 EPISODE 1

Transcript of 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu...

Page 1: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

v=1v=–1 v=–1 v=–1

v=–1 v=1

v=–1

optimaalin

en peli

O O

O

XX

O O

O

XXX X

O O

OX

XX X

OO

O

X

XX X

O

O OX

XX

O

O

O

X

XXO

O

O

O

O

X

XX XO

XO

XO

OX

2) 3)

5) 6) 7) 8) 9)

12)

O

O O

OX

XX XO

11)

O O

O

OX

XXO

XO

13)

OO

I N T R O D U C T I O N T O A R T I F I C I A L I N T E L L I G E N C E

D ATA 1 5 0 0 1

E P I S O D E 1

Page 2: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

1. L O G I S T I C S

2. W H AT I S A I ?

3. S C I F I V S R E A L I T Y

4. P H I L O S O P H Y O F A I

T O D AY ’ S M E N U

Page 3: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

D ATA 1 5 0 0 1 : I N T R O D U C T I O N T O A I

• Intermediate level course, 5 cu

• Organized by the Data Science MSc programme – Computers and Cognition module

• Elective course in the Computer Science BSc

Page 4: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

T E A M

• Lecturer: Teemu Roos, [email protected](but see below how to reach us)

• TAs: – Jarkko Savela – Matti Leinonen

• How to reach us: – link to Telegram group: https://t.me/IAI19 – you need to be registered; if you have any questions about

registration, please send email to [email protected]

Page 5: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

L E C T U R E S + E X E R C I S E S

• Lectures are not obligatory

• Material will be online: – materiaalit.github.io/intro-to-ai – these slides complement the material – additional material:

+ links to web sources, Youtube, literature + some of it is "nice-to-know", will be indicated if so

• Weekly exercises – make sure you are registered and attend the group to which

you registered – exercise points are gained by attending the exercise sessions

Page 6: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

T E S T M Y C O D E

• Programming exercises are downloaded bu NOT submitted through TMC

• Java or Python

• Instructions for installing the TMC to NetBeans for Java, or using a command-line TMC client for Python/Java are given on the github material

• Preinstalled NetBeans environment is available in B221 and BK107

Page 7: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

T E S T M Y C O D E

Page 8: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

P R E R E Q U I S I T E S

• Data Structures and Algorithms (or equivalent knowledge/skills): – queue, stack, traversals (depth/breadth/best-first, A*)

• Some university level maths: – most notably: probability calculus, conditional probability – the basic concept of vector calculus (addition)

• Programming skills: – we'll do a bit larger programs than in the intro courses

Page 9: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

G R A D I N G

• Exercises are mandatory: minimum 50% required to pass

• Grading based 33% on exercise points, 67% on final exam

• Completing 5/6 exercises gives you max. exercise points

• Exact grade limits will be decided later, "grading on a curve" to some extent – but typically people work so hard that the curve ends up being quite skewed (towards higher grades)

Page 10: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

• A different AI course: – usually at a later stage in the degree – less maths than usual (but lots of probability)

• Diverse student basis (BSc/MSc, major/minor): – hard to find a balance – constructive criticism is warmly welcomed

• Our goal: 100% student satisfaction and 100% pass

• Workload: 5 cu / 7 weeks = 18 hr / week

• No pain, no gain

M I S C

Page 11: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

T O P I C S

1. What is AI? History and Philosophy of AI

2. Games and Search

3. Logic (Programming)

4. Reasoning under Uncertainty and Machine Learning

5. Natural Language Processing

6. Robotics

"GOFAI"

"Modern AI"

Page 12: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

FA C T V S F I C T I O N

• AI in scifi: – Skyner (Terminator movies) – Winston (Dan Brown’s Origin) – HAL9000 (Space Odyssey) – Isaac Asimov’s Robot series (short stories) – Samantha (HER movie) 

Page 13: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

FA C T V S F I C T I O N

Discuss the following points:

• What capabilities do the AIs in scifi have?

• Which of these are not yet reality?

• Bonus question: Are the scifi-AIs self-conscious?

Page 14: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

T U R I N G T E S T

Page 15: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

T U R I N G T E S T

Page 16: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

T H E C H I N E S E R O O M ( S E A R L E )

• Is intelligent behavior possible without intelligence?

• Is a "mind" necessary for intelligent behavior?

• "Consciousness"?

Page 17: 5) 6) 7) 8) 9) INTRODUCTION TO · DATA15001: INTRODUCTION TO AI • Intermediate level course, 5 cu • Organized by the Data Science MSc programme – Computers and Cognition module

P H I L O S O P H Y O F A I

BEHAVIORTHINKING

HUMAN-LIKE

INTELLIGENT

"strong AI" "weak AI" rational agents "swarm intelligence"

cognitive science neuroscience psychology

Turing test