Machine Learning CSCI 5622

 

Fall 2004.

 

Location:          

Wednesdays 3:00pm-5:30pm ECCR 108

Instructor:

Professor Greg Grudic

Office:            

ECOT 525

Office Hours:

Tuesday and Wednesday 10:00 to 11:00

Phone:

303-492-4419

Email:

grudic@cs.colorado.edu

Course URL:

http://www.cs.colorado.edu/~grudic/teaching/CSCI5622_2004

 

Course Syllabus

 

Quizzes:

1. September 8.

2. October 6.

 

 

Homework:

·        Homework 1: Ridge Regression (Assigned: Sept. 15, 2004. Due: Oct. 6, 2004). Data sets X_trn.txt, Y_trn.txt, X_val.txt, Y_val.txt, X_tst.txt. Marking Homework_Mark_Part2.m

·        Homework 2: Gradient Classification Algorithms and Support Vector Machine Classification. (Assigned: Oct. 6, 2004. Due: Nov 3, 2004). Code for Linear Version.  Data sets X_2_trn.txt, Y_2_trn.txt, X_2_val.txt, Y_2_val.txt, X_2_tst.txt. Hints.

·        Homework 3: Stochastic and Deterministic Boosting, Random Forests Paper. (Assigned: Nov. 3, 2004. Due: Dec 6, 2004).

 

Project

 

Weekly Class Schedule:

 

  1. August 25: Introduction. Class Survey Survey.txt (email to me by end of week).
  2. September 1: Introduction to Regression. Demos.
  3. September 8: Generative and Discriminative Models for Classification.
  4. September 15:  Support Vector Machines Classification. Homework 1 Assigned (due Sept. 29).
  5. September 22:  Model Selection. Kernel Examples.
  6. September 29:   Support Vector Regression. Nearest Neighbor Algorithms. Classification and Regression Trees.
  7. October 6:  Neural Networks.  Perceptron Demo. Homework 1 due. Homework 2 Assigned (due Nov. 3).
  8. October 13:  Ensemble learning. Demo_Code_Bagging. Demo_Code_Boosting.
  9. October 20:  Bayesian Learning. Naïve Bayes. Learning with weighted examples (Code).
  10.  October 27:  Learning Algorithm Evaluation (demo).  Bayesian Learning. Naïve Bayes.  
  11.  November 3: Probably Approximately Correct (PAC) learning. Homework 2 due. Homework 3 Assigned (due Dec 6). Project Assigned (due Dec 12).
  12.  November 10: Review.
  13.  November 17: Midterm.
  14.  November 24: No Class (Thanksgiving).
  15.  December 1: . Reinforcement Learning.
  16.  December 8: Dimensionality Reduction. PCA. Spectral Clustering Unsupervised Learning. Review.