| 
View
 

FrontPage

This version was saved 12 years, 1 month ago View current version     Page history
Saved by mike@mbowles.com
on November 1, 2012 at 4:12:52 pm
 

 

Machine Learning 202

Organizer: Doug Chang

Instructors: Dr. Michael Bowles & Dr. Patricia Hoffman

 

We will cover several machine learning topics in detail.  Among those are Bayesian Belief Networks, Prof. Jerome Friedman's gradient boosting papers, svd's and recommender systems. 

 

For Machine Learning 202, we assume you are familiar with basic statistical concepts and have the ability to write programs running different algorithms on public data sets. We assume knowledge at the level of "Introduction to Data Mining" by Tan.  If you have taken our Machine Learning 101102 classes and Machine Learning 201, you are well prepared for this course.

 

We expect you to have previously used R.  We will use R for discussing homework problems and comparing different solution approaches.  .   http://cran.r-project.org/  For your review, R are here: References for R,  Reference for R Comments,  More R references.  To integrate R with Eclipse click here.

 

 

 

Machine Learning 202 Syllabus:  

 

Week  Topics  Homework  Links 
       
1st Week  Background for Ensemble Methods
 
 
  
Trees for Classification and Regression
  Trees  
     
 Learning Theory and AdaBoost   AdaBoost  
       
2nd Week       Gradient Boosting
  GradientBoostingLinks  
   
Analysis of AdaBoost
 
 
  
Friedman's Stochastic Gradient Boosting
 
 
       
3rd Week Random Forest and Performance Comparisons    
  Breiman's Random Forest Algorithm    
   Comparison of Machine Learning Algo's
   
4th Week  Active Learning & AdaBoost
 
 
     
 Active Learning
HW #2 Due  ActiveLearningLinks
   
 Learning Theory  & AdaBoost
 
AdaBoost  
       
4th Week  Recommender Systems
   
  
  Basic Background
HW #3 Due  EMLinks  
    
 EM for Gaussian Mixture Models
   
       
5th Week  More EM Applications
  RecommenderLinks  
  
LDA I
    LDA
    
 Hidden Markov Models
  hmm  
       

 

General Sequence of Classes:

 

Machine Learning 101:   Learn about ML algorithms and implement them in r  

     Text: "Introduction to Data Mining", by Pang-Ning Tan, Michael Steinbach and Vipin Kumar

Machine Learning 102:  Enable you to read and implement algorithms from current papers

     Text: "Introduction to Data Mining", by Pang-Ning Tan, Michael Steinbach and Vipin Kumar

 

Machine Learning 201:    Advanced Regression Techniques, Generalized Linear Models, and Generalized Additive Models    

     Text:  "The Elements of Statistical Learning - Data Mining, Inference, and Prediction"  by Trevor Hastie, Robert Tibshirani, and Jerome Friedman

Machine Learning 202:   Collaborative Filtering, Bayesian Belief Networks, and Advanced Trees

     Text:  "The Elements of Statistical Learning - Data Mining, Inference, and Prediction"  by Trevor Hastie, Robert Tibshirani, and Jerome Friedman

 

Machine Learning Big Data:  Adaptation and execution of machine learning algorithms in the map reduce framework.

 

Machine Learning Text Processing:  Machine learning applied to natural language text documents using statistical algorithms including  indexing, automatic classification (e.g. spam filtering) part of speech identification, topic and modeling, sentiment extraction

 

General Calendar for the Year:

Fall 2010: Basic Machine Learning Machine Learning 101 &  Machine Learning 102

Winter  2011:  Machine Learning 101 &  Machine Learning 201

Early Spring 2011:  Machine Learning 102 &  Machine Learning 202

 

We will be using the following text as a reference for 201 and 202:

 

"The Elements of Statistical Learning - Data Mining, Inference, and Prediction"  by Trevor Hastie, Robert Tibshirani, and Jerome Friedman.
This book is free to look at on line.  http://www-stat.stanford.edu/~tibs/ElemStatLearn

 

There are more Machine Learning References on Patricia's web site http://patriciahoffmanphd.com/

 

Be sure to sign up on the meetup page.

 

Comments (0)

You don't have permission to comment on this page.