CIS9603 Artificial Intelligence

Topics

Since today's AI is mostly learning and inference, we will focus on both subjects.
This course is designed as the first graduate course in learning and inference.
It introduces the basic concepts by focusing on their intuitive understanding and algorithmic perspective.
It is intended to prepare beginning graduate students for further graduate courses in machine learning, data mining, robotics, and computer vision.
The course project will focus on programming and practical experiments with our high end robot PekeeII from Wany Robotics (see the photo above).
The following list of topics is taken from the course book by Stephen Marsland.

Chapter 2 Linear Discriminants: Perceptron, Linear Separability, Linear Regression
Chapter 3 (The Multi-Layerd Perceptron)
Chapter 4 Radial Basis Functions: Weight Space, RBF Network, Curse of Dimensionality, Interpolation and Basis Functions
Chapter 5 Support Vector Machines: Optimal Separation, Kernels
Chapter 6 Learning with Trees: Decision Trees, Entropy, Classification and Regression Trees
Chapter 7 Decision by Committee: Ensemble Learning: Boosting, Bagging
Chapter 8 Probability and Learning: Bayes' Calssifer, Variance and Covariance, GMM, Nearest Neighbor Methods, Distance Measures
Chapter 9 Unsupervised Learning: k-Means, Vector Quantization, Self-Organizing Maps
Chapter 10 Dimensionality Reduction: Linear Discriminant Analysis (LDA), PCA, Kernel PCA, Multi-Dimensional Scaling
Chapter 11 Optimization and Search: Gradient Descent, Least-Squares Optimization, Tree Search, Hill Climbing, Simulated Annealing
Chapter 12 (Evolutionary Learning)
Chapter 13 (Reinforcement Learning)
Chapter 14 Markov Chain Monte Carlo Methods: Sampling, Proposal Distribution, MCMC, Metroplois-Hastings Algorithm, Gibbs Sampling
Chapter 15 Graphical Models: Bayesian Network, Inference with Gibbs Sampling, MRF, HMM, Kalman Filter, Particle Filter

Exams, Project and Grading

Homework: 10%

Class participation: 20%

Midterm (can be replaced by a midterm paper): 30%

Class project and its presentation: 40%

Homework: Homework due dates are on Friday. Late homework will result in a penalty. You will be allowed to drop your lowest three homework grades.

Class attendance: Class attendance is expected, and may be recorded from time to time. Absences for legitimate professional activities and illnesses are acceptable only if prior notice is given to the instructor by e-mail or phone. Scheduling conflicts with your work, extra-curricular activities, or any other such activities is not a valid excuse. Although attendance is not a specific part of the course evaluation it has a direct effect on class participation. If you are not in class you cannot participate. Class participation means that you attend class regularly and have completed your assigned readings. It means that you ask relevant questions and make informed comments in class. Class participation will contribute to the final grade.

Exams: If you miss a midterm for an emergency [as agreed ahead of time with the instructor], there will be no makeup exam: the other exams will become proportionally more important. If you miss any exam without prior agreement, and without definitive proof as to the reasons, you will get a zero.

Honor Code

All work submitted for credit must be your own.

You may discuss the homework problems with your classmates, the teaching assistant, and the instructor. You must acknowledge the people with whom you discussed your work, and you must write up your own solutions and code. Any written sources (apart from the text) used must also be acknowledged; however, you may not consult any solutions from previous years' assignments whether they are student or faculty generated.

Plagiarism will be handled with severe measures.

Please ask if you have any questions about the Honor Code. Violations of the honor code will be treated seriously. Please check the Temple University policy on Plagiarism and Academic Cheating.

Disabilities

I encourage students with disabilities, including "invisible" disabilities such as chronic diseases and learning disabilities, to discuss with us any appropriate accommodations that we might make on their behalf. Student must provide me with a note from the office of Disability Resources and Services at in 100 Ritter Annex, 215-204-1280, regarding their disability.

CIS9603 Artificial Intelligence

Fall 2010

Schedule

Instructor

Class

Textbook

Topics

Exams, Project and Grading

Honor Code

Disabilities