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_2005

 

Course Syllabus

 

 

 

Homeworks:

·        Homework 1: Equations from Code (Assigned: August 31, 2005. Due: September 15, 2005). Matlab Code (zipped). This assignment is worth 3% of your final mark.

·        Homework 2: Matlab Code From Equations (Assigned: September 7, 2005. Due: September 29, 2005). Matlab code: Demo_Gaussian_Kernel.m, Demo_Poly_Kernel.m, and Demo_Sigmoid_Kernel.m. This assignment is worth 3% of your final mark.

·        Homework 3: Kernel Ridge Regression (Assigned: September 21, 2005. Due: October 13, 2005). This assignment is worth 10% of your final mark.

- Data: The data for this homework is in X_lrn_HW3.txt and Y_lrn_HW3.txt. Example Matlab code for reading this data is in Read_HW3_Data.m.

·        Homework 4: Density Estimation and SVM Classification (Assigned: October 19, 2005. Due: December 16, 2005). You MUST use the template code in Template_Code.zip for your assignment! This assignment is worth 29% of your final mark.  (NOTE CHANGE IN DUE DATE AND ASSIGMENT!!!). Robot Data (robot_data.mat).

 

 

Class Project: Due December 14, 2005. The project is worth 25% of your final mark. (NOTE CHANGE IN DUE DATE!!!)

 

 

Quiz:

·        Take home quiz 1: Regression (Assigned: September 7, 2005. Due: September 21, 2005 at start of class). This quizz is worth 1% of your final mark.

 

 

 

Weekly Class Schedule:

 

  1. August 24: Introduction. Class Survey Survey.txt (email to me by end of week).
  2. August 31: Introduction to Regression.
  3. September 7: Introduction to Classification. Assumptions and Definitions.
  4. September 14: Perceptron Algorithm. Model Selection and Estimating Model Error.
  5. September 21: Support Vector Machine Classification.
  6. September 28: Support Vector Machine Classification.
  7. October 5: Support Vector Machine Classification. Support Vector Machine Regression.
  8. October 12: Support Vector Machine Regression. Model Selection and Estimating Model Error.
  9. October 19: Homework 4. Nearest Neighbor Classification and Regression. Classification and Regression Trees.
  10. October 26: Homework_4. Projects. Reinforcement Learning.
  11. November 2: Neural Networks.
  12. November 9: Ensemble learning (Boosting. Bagging, Random Forests).
  13. November 16: Probably Approximately Correct (PAC) learning.
  14. November 23: Thanksgiving – no class.
  15. November 30: Bayesian Learning. Naïve Bayes. Dimensionality Reduction. PCA. Unsupervised Learning (K-Means, Spectral Clustering).  Review
  16. December 7:  Midterm.