Xem mẫu
- Khoa Công nghệ thông tin
Trường Đại học Sư phạm Hà nội
TRÍ TUỆ NHÂN TẠO
Artificial Intelligence
Phạm Thị Anh Lê
Khoa CNTT - ĐHSP Hà nội
TTNT. p.1
- Nội Dung
Lec 1. Giới thiệu về TTNT, các khái niệm cơ bản
Lec 2. Agent thông minh
Lec 3. Giải quyết bài toán bằng tìm kiếm: tìm kiếm mù
Lec 4. Tìm kiếm kinh nghiệm (heuristics)
Lec 5. Tìm kiếm có đối thủ
Lec 6. Logic mệnh đề
Lec 7-8. Logic vị từ cấp một
Lec 9-10. Biểu diễn tri thức bởi các luật và lập luận
Lec 11-13. Lập trình logic Prolog
Lec 14-15. Tri thức không chắc chắn: logic xác suất,
logic mờ
TTNT. p.2
- Tài liệu tham khảo:
– Trí tuệ nhân tạo, by Đinh Mạnh Tường
– Trí tuệ nhân tạo: các phương pháp giải quyết vấn đề và kỹ
thuật xử lý tri thức, by Nguyễn Thanh Thủy
– Artificial Intelligence: A Modern Approach, by Stuart
Russell and Peter Norvig. (2nd ed)
– Citeseer - Scientific Literature Digital Library. Artificial
Intelligence-http://citeseer.nj.nec.com/ArtificialIntelligence/
- 2003
TTNT. p.3
- Overview (Giới thiệu tổng quan)
General Introduction
01-Introduction. [AIMA Ch 1] Course Schedule. Homeworks,
exams and grading. Course material, TAs and office hours. Why
study AI? What is AI? The Turing test. Rationality. Branches of
AI. Research disciplines connected to and at the foundation of AI.
Brief history of AI. Challenges for the future. Overview of class
syllabus. Agent
02-Intelligent Agents. [AIMA Ch 2] What is
sensors
effectors
an intelligent agent? Examples. Doing the right
thing (rational action). Performance measure.
Autonomy. Environment and agent design.
Structure of agents. Agent types. Reflex agents.
Reactive agents. Reflex agents with state.
Goal-based agents. Utility-based agents. Mobile
CS 460, Lecture 1
TTNT. p.4
agents. Information agents.
- Overview (cont.)
How can we solve complex problems?
03/04-Problem solving and search. [AIMA Ch 3]
Example: measuring problem. Types of problems.
9l
3l 5l
More example problems. Basic idea behind search Using these 3 buckets,
algorithms. Complexity. Combinatorial explosion measure 7 liters of water.
and NP completeness. Polynomial hierarchy.
05-Uninformed search. [AIMA Ch 3] Depth-first.
Breadth-first. Uniform-cost. Depth-limited.
Iterative deepening. Examples. Properties.
06/07-Informed search. [AIMA Ch 4] Best-first.
A* search. Heuristics. Hill climbing. Problem of
local extrema. Simulated annealing. Traveling salesperson problem
CS 460, Lecture 1
TTNT. p.5
- Overview (cont.)
Practical applications of search.
08/09-Game playing. [AIMA Ch 5] The
minimax algorithm. Resource limitations. Aplha-
beta pruning. Elements of
chance and non-
deterministic games.
tic-tac-toe
CS 460, Lecture 1
TTNT. p.6
- Overview (cont.)
Towards intelligent agents
10-Agents that reason
logically 1. [AIMA Ch 6]
Knowledge-based agents.
Logic and representation.
Propositional (boolean)
logic.
11-Agents that reason
logically 2. [AIMA Ch 6]
Inference in propositional
logic. Syntax. Semantics. wumpus world
Examples. CS 460, Lecture 1
TTNT. p.7
- Overview (cont.)
Building knowledge-based agents: 1st Order
Logic
12-First-order logic 1. [AIMA Ch 7] Syntax. Semantics. Atomic
sentences. Complex sentences. Quantifiers. Examples. FOL
knowledge base. Situation calculus.
13-First-order logic 2.
[AIMA Ch 7] Describing actions.
Planning. Action sequences.
CS 460, Lecture 1
TTNT. p.8
- Overview (cont.)
Representing and Organizing Knowledge
14/15-Building a knowledge base. [AIMA Ch 8] Knowledge
bases. Vocabulary and rules. Ontologies. Organizing knowledge.
An ontology
for the sports
domain
Kahn & Mcleod, 2000
CS 460, Lecture 1
TTNT. p.9
- Overview (cont.)
Reasoning Logically
16/17/18-Inference in first-order logic. [AIMA
Ch 9] Proofs. Unification. Generalized modus
ponens. Forward and backward chaining.
Example of
backward chaining
CS 460, Lecture 1
TTNT. p.10
- Overview (cont.)
Examples of Logical Reasoning Systems
19-Logical reasoning systems.
[AIMA Ch 10] Indexing, retrieval
and unification. The Prolog language.
Theorem provers. Frame systems
and semantic networks.
Semantic network
used in an insight
generator (Duke
university)
CS 460, Lecture 1
TTNT. p.11
- Overview (cont.)
Systems that can Plan Future Behavior
20-Planning. [AIMA Ch 11] Definition and goals. Basic
representations for planning. Situation space and plan space.
Examples.
CS 460, Lecture 1
TTNT. p.12
- Overview (cont.)
Expert Systems
21-Introduction to CLIPS. [handout]
Overview of modern rule-based
expert systems. Introduction to
CLIPS (C Language Integrated
Production System). Rules.
Wildcards. Pattern matching.
Pattern network. Join network.
CS 460, Lecture 1 CLIPS expert system shell
TTNT. p.13
- Overview (cont.)
Logical Reasoning in the Presence of
Uncertainty
22/23-Fuzzy logic.
[Handout] Introduction to
Center of gravity
fuzzy logic. Linguistic
Hedges. Fuzzy inference.
Examples.
Center of largest area
CS 460, Lecture 1
TTNT. p.14
- Overview (cont.)
AI with Neural
networks
24/25-Neural Networks.
[Handout] Introduction to
perceptrons, Hopfield
networks, self-organizing
feature maps. How to size a
network? What can neural
x 1(t)
networks achieve? w1
x 2(t)
w2 axon
y(t+1)
w
xn(t) 1 n
CS 460, Lecture
TTNT. p.15
- Overview (cont.)
Evolving Intelligent Systems
26-Genetic Algorithms.
[Handout] Introduction
to genetic algorithms
and their use in
optimization
problems.
CS 460, Lecture 1
TTNT. p.16
- Overview (cont.)
What challenges remain?
27-Towards intelligent machines. [AIMA Ch 25] The challenge
of robots: with what we have learned, what hard problems remain
to be solved? Different types of robots. Tasks that robots are for.
Parts of robots. Architectures. Configuration spaces. Navigation
and motion planning. Towards highly-capable robots.
28-Overview and summary. [all of the above] What have we
learned. Where do we go from here?
CS 460, Lecture 1 robotics@USC
TTNT. p.17
- Artificial Intelligence?
Intelligence? Trí năng, trí tuệ, trí thông
minh
Thế nào là Artificial intelligence? Chúng ta
sẽ phân tích 4 loại quan niệm về
intelligence sau:
CS 460, Lecture 1
TTNT. p.18
- Trí tuệ nhân tạo là gì?
“Nỗ lực tạo ra các máy tính “Việc nghiên cứu các năng lực trí
biết tư duy … máy tính có ý tuệ sử dụng các mô hình tính toán
thức (The exciting new effort (The study of mental faculties
to make computers thinks … through the use of computational
machine with minds, in the full models)”
and literal sense)” (Charniak et al. 1985)
(Haugeland 1985)
“Nghệ thuật sáng tạo ra các “Nghiên cứu tìm cách giải thích và
máy thực hiện các chức năng mô phỏng các hành vi thông minh
đòi hỏi sự thông minh như khi bằng các quá trình tính toán (A field
thực hiện bởi con người (The of study that seeks to explain and
art of creating machines that emulate intelligent behavior in terms
perform functions that require of computational processes)”
intelligence when performed (Schalkol, 1990)
by people)” (Kurzweil, 1990)CS 460, Lecture 1
TTNT. p.19
- Trí tuệ nhân tạo: Hệ thống tư
duy như con người
“Nỗ lực tạo ra các máy tính Hệ thống tư duy như con
biết tư duy … máy tính có ý người
thức (The exciting new effort (Systems that think
to make computers thinks …
machine with minds, in the full
like humans)
and literal sense)”
(Haugeland 1985)
Ví dụ: Newell&Simson
(1961) phát triển GPS
Con người tư duy như thế (General Problem Solving)
nào? Chưa có câu trả lời bắt chước cách giải quyết
chính xác trong rất nhiều các bài toán trong toán học
tình huống. của con người.
CS 460, Lecture 1
TTNT. p.20
nguon tai.lieu . vn
