Scribd
Upload
75 views

2021 Slide1-Introduction Eng

Dr. Nguyễn Văn Vinh is a lecturer and AI expert at UET in Hanoi who received his PhD from JAIST in Japan. His research focuses on AI, natural language processing, and big data. This document provides an introduction and overview of his artificial intelligence course, including prerequisites, grading, course topics, and a brief history of AI achievements and techniques.

Uploaded by

hoang anh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
75 views

2021 Slide1-Introduction Eng

Dr. Nguyễn Văn Vinh is a lecturer and AI expert at UET in Hanoi who received his PhD from JAIST in Japan. His research focuses on AI, natural language processing, and big data. This document provides an introduction and overview of his artificial intelligence course, including prerequisites, grading, course topics, and a brief history of AI achievements and techniques.

Uploaded by

hoang anh
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 47

Artificial Intelligence

Dr. Nguyễn Văn Vinh


CS Department, Information
Faculty-UET

1
Introductor

• Dr. Nguyễn Văn Vinh


• PhD in JAIST (Japan Advanced Institute of Science and Technology)
• Research focus: AI, Natural Language Processing, Big Data
• Lecturer, AI Expert - UET– Hanoi VNU
• Senior Data Scientist,Công ty QAI, Fsoft
• Design Leader of Machine Learning course for FUNiX – Online
University (https://vnexpress.net/giao-duc/funix-ra-mat-chuong-
trinh-machine-learning-3986011.html)
• Principle Investigator of National KC Project: “Phát triển hệ thống
dịch đa ngữ giữa tiếng Việt và một số ngôn ngữ khác”, 2020-
2022.
• Teaching some ML, NLP Lectures in Samsung, BigData Vin, Viettel,
…

2
Artificial Intelligence

• Instructor: Dr. Nguyen Van Vinh, CS Department, Information


Faculty.
Email: [email protected], [email protected]
Tel: 0912263062
• Course web page: https://courses.uet.vnu.edu.vn/ choose AI
course.
• Up to date information
• Lecture notes
• Relevant dates, links, etc.
• References:
• Lecture Slides
• https://stanford-cs221.github.io/autumn2019/#coursework
• Đinh Mạnh Tường: Trí Tuệ Nhân Tạo. NXB Khoa Học Kỹ Thuật 2002
• Từ Minh Phương: Giáo trình Nhập môn Trí Tuệ Nhân Tạo, 2016
• [AIMA] Artificial Intelligence: A Modern Approach, by Stuart
Russell and Peter Norvig. (3nd ed)

3
Artificial Intelligence: A Modern Approach, 2020
(http://aima.cs.berkeley.edu/ )

4
Your Helpful TAs

• Master Nguyễn Minh Thuận


• Nguyễn Hoàng Quân

5
Artificial Intelligence

• Course overview: foundations of symbolic intelligent systems.


Agents, search, problem solving, logic, representation, reasoning,
machine learning, natural language processing & computer
vision.

• Prerequisites: Programming principles, discrete mathematics for


computing, software design and software engineering concepts.
Good knowledge of C++, Java, Python. Python required for
programming assignments.

• Grading: 30% for (midterm + homeworks/assignments ) +10%


for attendence + 60% for final

6
Policy & Practical issues

• Encourage discussion but assignments must be your individual work


• Codes copied from books or other libraries but be explicitly
acknowledged
• Sharing or copying codes is strictly prohibited.

7
AI course of Stanford 2017

8
Why study AI?

9
Some achievements of
Artificial Intelligence

10
Google Translate & Vietgle
Translate

11
AlphaGo
• 3-2016, Alphago
defeated Lee Sedol,
the Korean go
grandmaster 4-1,
made a surprised
both professional
goers and AI
researchers.

• 2017, AlphaGo Zero,


which beat the
original AlphaGo
system 100—0.

12
Image Net (better than Human)
 The best image classification system declined from
26% error in 2011 to 3.1% in 2016 equivalent and
lower than humans.

13
Image Net (better than Human)

14
Virtual Assistant

 Apple's Siri, Google


Now, Microsoft Cortana,
Amazon Echo, và other
assistants.
 Thanks to breakthrough
innovation of speech
recognition (ASR) in the
last 7 years.
 However, ASR is only a
phase, and another
phase is understanding
the text, this is a very
difficult problem.

15
Self-driving cars

• Google, Uber, Tesla self-driving cars: Currently


expanding the evaluation and testing on many
16 roads / Available for 2017-2020?
Modern AI

• Subject of intense study:


•Nearly ever CS department has at least 1 AI group.
•Heavily funded (NSF, DARPA, EU, etc.).
•Google, Amazon, Microsoft, Baidu etc.
•~ 700 PhDs a year in the US
•Thousands of research papers written every year.

• CS department in Vietnam has at least 1 AI group or AI


domain.

17
AI jobs in 2020

18
Companies

19
Companies (Vietnam)

• VinAI/Vin BigData Academy


• FPT.AI
• Viettel-AI
• Zalo.AI
• …

20
Governments

Vietnam? (Itrithuc.vn), AI4Life, AI4VN

21
What is AI?

• “AI is the science and engineering of making intelligent machines


which can perform tasks that require intelligence when performed
by humans …”

22
What is AI?

Views of AI fall into four categories (bốn loại):


Lý trí vs. con người (human are not perfect)
Hành động vs. Suy nghĩ

Thinking humanly Thinking rationally

Acting humanly Acting rationally

23
Alan Turing - Father of AI
Alan Turing (OBE, FRS)
• Born 23 June 1912, Maida Vale,
London, England
• Died 7 June 1954 (aged 41),
Wilmslow, Cheshire, England
• Fields: Mathematician, logician,
cryptanalyst, computer scientist
• Institutions:
• University of Manchester
• National Physical Laboratory
• Government Code and Cypher
School (Britain's codebreaking
centre) Alan Turing memorial
• University of Cambridge statue in Sackville Park,
Manchester

24
Alan Turing

• The history of AI begins with the following articles:


• Turing, A.M. (1950), Computing machinery and intelligence, Mind,
Vol. 59, pp. 433-460.

25
Acting Humanly: The Turing Test

• Alan Turing's 1950 article Computing Machinery and


Intelligence discussed conditions for considering a
machine to be intelligent

• “Can machines think?”  “Can machines behave


intelligently?”
• The Turing test (The Imitation Game): Operational definition of
intelligence.

26
Acting Humanly: The Turing Test

• Computer needs to possess: Natural language processing,


Knowledge representation, Automated reasoning, and Machine
learning

27
Branches of AI

28
Artificial Intelligence in diverse subject

29
30
31
32
33
AI: a brief history (1)

34
AI: a brief history (2)

35
AI: a brief history (3)

36
AI: a brief history (4)

37
AI: a brief history (5)

38
AI: a brief history (6)

39
AI: a brief history (7)

40
AI: a brief history (8)
 2000-present: Statistics
 Machine Learning
 Traditional models: Hidden Markov models (HMM), support
vector machines (SVM), Gaussian processes, graphical
models (Bayes networks, conditional random fields)
 Data mining
 2010- present: Deep Learing

41
42
AI State of the art

• Deep Blue defeated the reigning world chess champion Garry Kasparov in
1997.
• Deep Fritz defeated Kramnik in 2006.
• Proved a mathematical conjecture (Robbins conjecture) unsolved for
decades
• No hands across America (driving autonomously 98% of the time from
Pittsburgh to San Diego)
• During the 1991 Gulf War, US forces deployed an AI logistics planning and
scheduling program that involved up to 50,000 vehicles, cargo, and people
• NASA's on-board autonomous planning program controlled the scheduling
of operations for a spacecraft
• Proverb solves crossword puzzles better than most humans
• Zezo-Go system
• Google translation system
• Object (face) recognition system
• Vitual Assistant
• DeBert (Microsoft) surpasses human performance on the SuperGLUE
benchmark (August, 2019).
Characteristics of AI tasks

• High societal impact (aect billions of people)


• Diverse (language, games, robotics)
• Complex (really hard)

44
Resources

45
Course Overview
• Problem Solving using search techniques:
• Blind search.
• Informed search
• Constraint satisfaction problem.
• Game Playing:
• Adversarial Search
• Knowledge Representation:
• Propositional logic
• Predicate logic
• Reasoning mechanisms
• Probabilistic reasoning
• Machine Learning:
• Machine Learning e.g. Naive Bayes, neural network, deep learning,
Reinforcement Learning
• Natural Language Processing & Computer Vision

46
Summary

• There’s no magic in AI. It’s all about math, computer science, and
smart ways to relate them to real problems
• AI is a fast-moving exciting area
• We can directly make the world a better place
• This course will teach you the foundations

47

You might also like