ICSI535 Artificial Intelligence I

Instructor Feng Chen
Office UAB-426
Number (518) 442-4270
Email fchen5@albany.edu
Office Hour
Wednesday: 1:00PM to 2:00PM
Thursday: 10:00AM to 11:00AM

TA
Chunpai Wang
Office UAB 433
Number  
Email cwang25@albany.edu
Office Hour
Tuesday 12:00PM to 1:00PM
Thursday 12:00PM to 1:00PM

TA
Erkang Xie
Office UAB 433
Number  
Email exie@albany.edu
Office Hour
Tuesday 3:00PM to 5:00PM
Thursday 2:30PM to 4:30PM

TA
Harinder Singh
Office UAB 433
Number  
Email ssingh22@albany.edu
Office Hour
Monday 1:15PM to 3:15PM
Friday 1:15PM to 3:15PM

Class Time and Location Th 5:45PM - 8:35PM, HU-137
Class Website http://www.cs.albany.edu/~fchen/course/ICSI-2016-535/

Course Postings

Course Description:

A first course in artificial intelligence (AI) introducing basic concepts and techniques. Topics include statistics, optimization, first order logic, probabilistic soft logic, Markov model and hidden Markov models, Markov random fields, and Artificial Neural networks.

TextBook


Authors: Stuart Russel and Peter Norvig
ISBN-10: 9332543518
ISBN-13: 978-9332543515
Publisher: PE; 3 edition(2015)
Textbook Website: http://aima.cs.berkeley.edu/

Course Description:

Part Lecture Lecture Topics Notes
A: Statistics 1 Basic Distribution (Binomial, Poisson, Gaussian)  
2 Parameter Esitmation (Maximum Likelihood Estimation)  
B: Numerical Optimization Techniques 3 Gradient, SubGradient
Gradient Descent, Project Gradient Descent
4 Parallel Algorithms (The alternating direction method of multipliers)  
C: First Order Logic 5 Syntax and Semantics
Learning and Inference
D: Probablistic Soft Logic 6 Syntax and Semantics
Learning and Inference
E: Markov Model and Hidden Markov Model 7 TBD
F: Markov Random Fields 8 TBD
9 TBD
G: Artificial Neural Networks 10 TBD
11 TBD

Examinations and Grading:

Homework


Course Project Requirement

Course Project teams:

to be announced

Policy on Cheating: 

Cheating in an exam will result in an E grade for the course. Further, the students involved will be referred to the Dean's o ce for disciplinary action.

Homework problems are meant to be individual exercises; you must do these by yourself. Any of the following actions will be considered as cheating.

  1. A solution which is identical to or nearly identical to the solution submitted by another student in the class
  2. A solution which is identical to or nearly identical to the solution provided by the instructor in a previous o ering of CSI 431/531
  3. A solution which is identical to or nearly identical to a solution available on the Internet.

Cheating in a homework exercise will result in the following penalty for all the students involved.

  1. The homework in which cheating occurred will be assigned a grade of ZERO.
  2. The homework in which cheating occurred will be assigned a grade of ZERO.

Students who cheat in two or more homeworks will receive an E grade for the course. The names of such students will also be forwarded to the Dean's oce for disciplinary action.