DATA130008: Introduction to Artificial Intelligence
Time and Location: Wednesday from 9:55 am to 12:30 pm in H6405
- Wei, Zhongyu 魏忠钰
- Office: N202 Zibin Building (子彬院 北202)
- Email: firstname.lastname@example.org
- Office Hour: Wednesday from 4:00pm to 5:30pm, or by appointment.
- Fan, Zhihao 范智昊
- Qi, Jitong 祁季桐
- Wang, Siyuan 王思远
- Ye, Rong 叶蓉
Artificial Intelligence (AI) aims to make a computer that can learn, plan and solve problems autonomously.
AI applications include web search, speech recognition, face recognition, machine translation, autonomous driving, and automatic scheduling, etc.
In this course, you will learn fundamental principles and techniques that drives such applications and have a chance to implement some of them.
Specific topics include search, constraint satisfaction, game playing, Markov decision processes and logic.
The main goal of the course is to equip students with the tools to tackle real problems in the era of big data.
Textbooks and Reference
- Stuart J. Russell, Peter Norvig (2009) Artificial Intelligence A Modern Approach, 3rd Edition.2009, Prentice Hall
March 12th, 2018: Download the tentative version of syllabus [here]!
March 8th, 2018: The course website is up!
- Out: May 25th, 2018
- Due: June 10, 2018
- TA in Charge: Ye, Rong
- Out: May 9th, 2018
- Due: May 27th, 2018
- TA in Charge: Wang, Siyuan
- Out: April 19th, 2018
- Due: May 6th, 2018
- TA in Charge: Qi, Jitong
- Out: March 23rd, 2018
- Due: April 15th, 2018
- TA in Charge: Fan, Zhihao
Gomoku Rule: Freestyle
- Baseline(35%): Full marks if your AI's rating is higher than the rating of MUSHROOM
- Report(15%): No more than 4 pages
- Rating(50%): (your rating - lowest rating)/(highest rating - lowest rating)
For more inforamtion, please check slide of lab2.
Lab - 4: Bayes Networks
Lab - 3: Reinforcement Learning
- Time: May 9th
- Topic: reinforcement learning [slides] [solution]
- TA in Charge: Wang, Siyuan
Lab - 2: Adverarial Search
Lab - 1: Search Algorithm
- Topic: Hidden Markov Model [7.0] [7.1] [7.2]
- Reading: Russell and Norvig CH15.1-15.5
- Topic: Reinforcement Learning [6.1]
- Reading: Russell and Norvig CH21.1-21.4
- Topic: Markov Decision Process [5.1] [5.2]
- Reading: Russell and Norvig CH17.1-17.3
- Topic: constraints satisfactory problems, local search [4.1]
- Reading: Russell and Norvig CH6, CH4.1-4.2
- Topic: adversarial game, utility [3.1] [3.2]
- Reading: Russell and Norvig CH5, CH16.1-16.3
- Topic: informed search[2.1]
- Reading: Russell and Norvig CH3.5-3.6
- Topic: introduction to AI, uninformed search [1.0] [1.1]
- Reading: Russell and Norvig CH1, CH2, CH3.1-3.4
- 4 Projects (50%)
- 1 Competition Project (10%)
- 1 Final Exam(30%)
- Labs and Participation (10%)
- Do collaborate and discuss together, but write up and code independently.
- Do not look at anyone else’s write-up or code.
- Do not show anyone else your write-up or code or post it online.
- We will your code irregularly. If plagiarism is identified, the mark for that project will be ZERO.
Many thanks to the UC Berkeley, Stanford, University of Toronto, Carnegie Mellon University, UT Dallas and Tianjin University for sharing material used in slides and homeworks.