COURSE SYLLABUS AND OUTLINE
CSE 4705 – 001
LH 205, Mon/Wed 3:00pm — 4:15pm
This class has 1-2 lab as needed.
Office hours: Tue 1:00pm — 3:00pm
Office: ITEB 233
Xingyu Cai / Xia Xiao
Email 1: firstname.lastname@example.org
Cai office hours: Fri 2-3pm, BECAT A22
Xiao office hours: Fri. 2-3pm ITEB 221
Course website: http://jinbo-bi.uconn.edu/Spring2015_Artificial_Intelligence
PURPOSE AND APPROACH:
The purpose of this course is to introduce students the basic research areas in artificial intelligence (AI), to study several techniques in depth in selected topics of AI, and to apply these techniques in real-life AI projects that involve big data competitions. AI is a huge field, including many subareas such as knowledge representation, reasoning, machine learning, data mining, robotics and natural language processing etc. This course aims to cover some basic topics as well as some state of the art. Basic areas such as intelligent agents, searching and first-order logic will be studied. However, a significant effort will also be given to learning, learning from massive examples/big data and statistical learning. Throughout the course, substantial projects will be designed that are based on real-life data challenges, and students will be asked to form teams and each team can choose from the designed projects to work towards their course projects.
The course will consist of lectures, demonstrations, term projects and potential laboratories. Lectures will serve as the vehicle to introduce concepts and knowledge to students. Demonstrations aim to bring some concrete sense and experience with how AI works. As part of the course, students will work on a term project with the goal of applying any learning techniques to a problem selected from a list of projects. Teams of four-six students will be created for each project. Each team is required to present in the classroom and submit a project report, which includes the definition of the problem, techniques used to solve the problem and experimental results obtained. This exercise will help the team gain a hands-on understanding of the material studied in this course and promotes collaborations among team members. Programming-based laboratories may be arranged. If a reasonable number of students are not familiar with the programming language used to complete homework assignments, laboratories can be arranged to help.
1. Required textbook
Artificial Intelligence: A Modern Approach (3rd edition) by Stuart Russell and Peter Norvig, ISBN-10: 0136042597
This book is a required textbook for this course. It is a large book, providing a broad introduction to many aspects of AI. We will only study a subset of the materials. Students can read this book to learn other areas that are not covered in this course.
2. Optional textbooks
- Introduction to Data Mining by Pang-Ning Tan, Michael Steinbach, and Vipin Kumar, ISBN-10: 0321321367
- Pattern Recognition and Machine Learning (Information Science and Statistics) by Christopher M. Bishop, ISBN-10: 0387310738
The above two books are supplementary to the required text on the machine learning and data mining subareas. When we cover materials from these two books, slides or lecture notes will be provided for additional reading.
COURSE WORK AND GRADING:
Basically the course covers two major components: the traditional topics and the more state-of-the-art topics. The first component will be evaluated using 2-3 assignments and a mid-term exam whereas the second component will be evaluated in 0-1 assignment and the final term project. The instructor will design term projects around the second set of topics. Students will choose a project from the pre-designed projects.
1. Programming-involved homework assignments (3): 30%
In the first part of the course, we will have 2-4 programming assignments, which can be implemented by a specific programming language. If a student decides to use another programming language, please discuss it with the TA of the course to see whether his assignments can be graded.
2. Mid-term exam (1): 30%
This exam will be an in-class
3. Term Project (1): 40% a team can consist of 4-6 students and students of the team altogether work on a substantial project that is chosen from a list of projects.
Week 1 Introduction
Week 2 Intelligent agents
Week 3 Problem solving and searching, informed searching
Week 4 Informed search algorithms
Week 5-6 Constraint satisfaction problems, game playing
Week 7 Logical agents
Week 8 First-order logic
Week 9 mid-term and review
Week 10 Basics in learning
Week 11 Support vector machines
Week 12 Neural networks
Week 13 Review, project preparation, and potentially other learning algorithms
Week 14 Project preparation and presentation
COURSE POLICY AND ARRANGEMENT:
- Computers are allowed in classroom for taking notes or any activity related to the current class meeting.
- Participation in lectures is highly encouraged.
- TA Xia Xiao will be responsible for grading HW 2 and HW3.
- TA Xingyu Cai will be responsible for grading HW1, mid-term exam and term projects.
- No make-up plan is designed for missing homework assignments. Please do your best to turn them in.
- If you miss the mid-term exam and bring back a doctor note, you will be eligible to take a make-up exam.
A HuskyCT site will be set up for the class. You can access it by logging in with your NetID and password. You must use HuskyCT for submitting assignments. The instructor uses the HuskyCT announcement to announce class materials, grades, problem clarifications, changes in class schedule, and other class announcements.
Three projects will be designed and listed at the course website with necessary materials by the end of the fifth week. Student teams can choose from these projects.
Tools that may help with course projects
- Matlab Optimization Toolbox
- SVM_Light (support vector machines)
- LIBSVM (support vector machines)
- Bayesian Knowledge Discoverer (BKD): computer program able to learn Bayesian Belief Networks from databases
- Bayes net toolbox for Matlab
- TSP Demo
- LeNet (neural networks)
- Neural networks demo
- Neural networks flash demo
- GAUL (genetic algorithm)
- Java genetic algorithm demo
- A complete notebook GA
- A system for distributing statistical software, datasets, and information by electronic mail, FTP and WWW
- Tools for mining large databases C5.0 and See5
- Description of the SLIPPER rule learner, that is a system that learns sets of rules from data based on original RIPPER rule learner
- Information about Data Mining and knowledge discovery in Databases
- Clustering Algorithms
You are expected to adhere to the highest standards of academic honesty. Unless otherwise specified, collaboration on assignments is not allowed. Use of published materials is allowed, but the sources should be explicitly stated in your solutions. Violations will be reviewed and sanctioned according to the University Policy on Academic Integrity. Collaborations among team members are only allowed for the final term projects that are selected.
Academic integrity is the pursuit of scholarly activity free from fraud and deception and is an educational objective of this institution. Academic dishonesty includes, but is not limited to, cheating, plagiarizing, fabricating of information or citations, facilitating acts of academic dishonesty by others, having unauthorized possession of examinations, submitting work for another person or work previously used without informing the instructor, or tampering with the academic work of other students.
If you have a documented disability for which you are or may be requesting an accommodation, you are encouraged to contact the instructor and the Center for Students with Disabilities or the University Program for College Students with Learning Disabilities as soon as possible to better ensure that such accommodations are implemented in a timely fashion.
Jinbo Bi 2014 /12-2014/12
Last revised: 01/21/2015