"You can't stop the signal, Mal. Everything goes somewhere, and I go everywhere."
-- Mr. Universe, from the movie "Serenity"

Course Description

This course is part of the University of Idaho series on Artificial Intelligence and Machine Learning which comprises these three courses: Artificial Intelligence, Machine Learning, and Evolutionary Computation. The course is basically new. (However, if you took AI under me a year ago, you cannot take this course because that course was a prototype for this course. There is a lot of overlap.)

We will focus on the machine learning half of Artificial Intelligence. This includes algorithms to learn behavior, classify data, and predict behaviors and/or data given past data. This is an implementation course. We will implement some of the important algorithms of machine learning and apply them to small problems (usually under 10K samples of data). This is a course about the algorithms and not about using pre-made tools to do machine learning and data mining. We will look at topics such as decision trees, neural networks, deep learning, Markov brains, and reinforcement learning. There will be lots of programming in C/C++ and algorithm work. Proficiency in programming in C/C++ is required as well as a solid understanding of undergrad math including an understanding of basic probability and statistics, calculus, and linear algebra. Algorithm descriptions will be given in Python and demonstrations in Mathematica (purchase not required).

Time: 1:30-2:30
Final: 504 students are required to create a final project and report. No final.
Location: JEB 026
Text: Textbook:
Machine Learning: An Algorithmic Perspective by Stephen Marsland (Second Edition!)

Estimated Syllabus

This syllabus is an estimate of what we might cover this semester. The class varies from semester to semester to reflect new and interesting topics.

Week

Monday
of that
Week

 Topics/Links Assignments Comments
wk 1 Jan 9 Artificial Intelligence, Machine Learning, Data Analytics the big picture, Learning vs Prediction, The classes of problems Read Chapter 1 NO CLASS MONDAY
wk 2 Jan 16 Treating the input, measuring the quality of output, are we successful Read chapter 2   NO CLASS MONDAY
wk 3 Jan 23 Neural networks and backprop Read chapter 4  
wk 4 Jan 30 Neural networks continued, NEAT and HyperNEAT, deep learning in NN Assignment 1  
wk 5 Feb 6 Dimensionality reduction and PCA Read chapter 6  
wk 6 Feb 13 PCA continued Assignment 3  
wk 7 Feb 20 K-means and nearest neighbor    
wk 8 Feb 27 K-means    
wk 9 Mar 6 Assignment 4  
xx Mar 13 Decision Trees     SPRING BREAK!
wk 10 Mar 20 Decision Trees    
wk 11 Mar 27 Association Rules    
wk 12 Apr 3 Association Rules Assignment 5  
wk 13 Apr 10 Reinforcement Learning, Q-Learning, Sarsa, eligability traces    
wk 14 Apr 17 Bayesian Networks Assignment 6  
wk 15 Apr 24 Bayesian Networks continued    
wk 16 May 1 Stochastic Learning with the EM algorithm    
wk 17 May 8 Finals Week Final: None  

References and Resources

Services

Policies and Processes

Fun Stuff