AI p0 introduction to AI course

Nguyễn Thị Hải Bình Khoa Công nghệ thông tin Đại học Giao thông vận tải... WHAT IS BIOLOGICAL INTELLIGENCE?• Sensory processing xử lý giác quan • Visual cortex vỏ thị giác • Auditory cor

Trang 1

GIỚI THIỆU VỀ TRÍ TUỆ

NHÂN TẠO

GV Nguyễn Thị Hải Bình Khoa Công nghệ thông tin Đại học Giao thông vận tải

Trang 2

AI IN FICTION

Trang 3

AI IN REALITY

GV Nguyễn Thị Hải Bình 3

Trang 5

Trang 6

WHAT IS BIOLOGICAL INTELLIGENCE?

• Sensory processing (xử lý giác quan)

• Visual cortex (vỏ thị giác)

• Auditory cortex (vỏ thính giác)

• Somatosensory cortex (vỏ xúc giác)

• Motor cortex (vỏ vận động)

• Cognitive functions (chức năng nhận thức)

• Memory (ghi nhớ)

• Reasoning (suy luận)

• Executive control (kiểm soát điều hành)

Trang 7

WHAT IS BIOLOGICAL INTELLIGENCE?

• A mix of general-purpose and special-purposealgorithms

• General-purpose

• Memory formation, updating, retrieval

• Learning new tasks

• Special-purpose

• Recognizing visual patterns

• Recognizing sounds

• Learning language

• All are integrated seamlessly

Slide credit: Joelle Pineau (jpineau@cs.mcgill.ca) 7

Trang 8

WHAT IS AI?

• “The exciting new effort to make computers think

… machines with minds.” (Haugeland, 1985)

• “The automation of activities that we associate with human thinking, activities such as decision-making, problem solving, learning …” (Bellman,1979)

• “The art of creating machines that performfunctions that require intelligence when perform

by people.” (Kurzwell, 1990)

Trang 9

WHAT IS AI?

• “The study of mental faculties through the use of

computational models.” (Charniak and McDermott,1985)

• “The study of the computations that make itpossible to perceive, reason, and act.” (Winston,1992)

• “Computational Intelligence is the study of thedesign of intelligence agents ” (Poole et al., 1998)

Trang 10

WHAT IS AI?

Thinking Humanly

(Suy nghĩ như con người)

Thinking Rationally (Suy nghĩ hợp lý)

Acting Humanly (Hành động như con người)

Acting Rationally (Hành động hợp lý)

Trang 11

ACTING HUMANLY: TURING TEST

• AI is all about duplicating what the human braindoes

• Can a machine think?  If it could, how would wetell? (Alan Turing)

• Turing test

• Loebner contest

Trang 12

ELIZA AND ALICEBOT

• Remarkably simple “Rogerian Psychologist”

• Uses Pattern Matching to carry on limited form ofconversation

• Seems to “Pass the Turing Test!” (McCorduck, 1979,

pp 225-226)

• http://www.lpa.co.uk/pws_dem4.htm

• http://www.alicebot.org/

Trang 13

ACTING RATIONALLY (HÀNH ĐỘNG HỢP LÝ)

• Rational behavior = doing the “right” thing

• Doing what is expected to maximize goal

achievement, given the available information and

available resources.

• Does not necessarily require thinking (e.g blinking reflex).

• But in many cases, thinking serves rational behavior.

• This is the flavor of AI we will focus on.

Trang 15

Artificial Intelligence: A Modern Approach (3nd ed.), Figure 2.2 A vacuum-cleaner world with just two locations

Trang 17

EARLY AI HOPES AND DREAMS

• Make programs that exhibit similar signs ofintelligence as people: prove theorems, play chess,have a conversation

• Logical reasoning was key

• Learning from experience was consideredimportant

• Building general problem solvers.

• There was a lot of hope that natural language

could be easily understood and processed.

Trang 18

• Reasoning is now the part named ``AI''

• A lot of progress was made in this way!

• Some recent efforts try to put all this together (e.g

in robotics)

Trang 19

AI SYSTEM: CHESS PLAYING (1997)

• IBM Deep Blue defeats Garry Kasporov

• Perception: advanced features of the board

• Action: choose a move

• Reasoning: search and evaluation of possible board positions

Slide credit: Joelle Pineau (jpineau@cs.mcgill.ca)

19

Trang 20

AI SYSTEM: POKER PLAYING (2008)

Trang 21

AI SYSTEM: IBM WATSON (2011)

21

Trang 23

AI SYSTEM: MEDICAL DIAGNOSIS

(1992)

• Pathfinder (D Heckerman, Microsoft Research)

• Perception: symptoms, test result.

• Action: suggest tests, make diagnosis.

• Reasoning: Bayesian inference, machine learning, Monte-Carlo simulation.

23

Trang 24

AI SYSTEM: READING THE MIND

(2008)

• Brain Image Analysis (T Mitchell, CMU)

• Perception: brain imaging using fMRI technology.

• Actions: detect which word (e.g “hammer”,

“apartment”, …) is being read by the human subject.

• Reasoning: statistical machine learning.

Trang 25

AI SYSTEM: HANDWRITING

RECOGNITION (2003)

Slide credit: Joelle Pineau

Trang 26

AI SYSTEM: OBJECT RECOGNITION

(2014)

• ImageNet Large Scale Visual Recognition Challenge

• Image database with 1000 object categories.

• Hundreds of example images for each class

• Over 1 million images in total

• Current best results: 7% classification error.

Trang 27

AI SYSTEM: AUTONOMOUS DRIVING

• ALVINN (D Pomerleau, CMU) 1998

27

Trang 28

STANLEY (STANFORD UNIVERSITY) 2005

Trang 29

GOOGLE SELF-DRIVING CAR (2014)

Trang 30

AI SUB-AREAS

Human Intelligence: Artificial Intelligence:

• Sensory processing

• Visual cortex  Computer vision

• Auditory cortex  Signal/speech processing

• Somatosensory cortex  Haptics

• Motor cortex  Robotics

• Cognitive functions

• Memory  Knowledge representation

• Reasoning  Search, inference

• Executive control  Planning, decision-making

Trang 31

GIỚI THIỆU MÔN HỌC

GV Nguyễn Thị Hải Bình Khoa Công nghệ thông tin Đại học Giao thông vận tải

Trang 32

GIỚI THIỆU MÔN HỌC

Trang 33

TÀI LIỆU THAM KHẢO

• Artificial Intelligence: A modern approach, Stuart

Russell and Peter Norvig, Pearson Education, Inc., 2010

Trang 34

NỘI DUNG MÔN HỌC

• Giải quyết vấn đề bằng tìm kiếm

• Các chiến lược tìm kiếm mù

• Các chiến lược tìm kiếm kinh nghiệm

• Các chiến lược tìm kiếm tối ưu

• Các chiến lược tìm kiếm có đối thủ

• Tri thức và lập luận

• Logic mệnh đề và logic vị từ

• Biểu diễn tri thức bằng luật

• Suy diễn tiến và suy diễn lùi

Định dạng
Số trang	34
Dung lượng	2,21 MB