| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • You already know Dokkio is an AI-powered assistant to organize & manage your digital files & messages. Very soon, Dokkio will support Outlook as well as One Drive. Check it out today!

View
 

NotesWeek3

This version was saved 13 years, 2 months ago View current version     Page history
Saved by hoffman.tricia@gmail.com
on January 27, 2011 at 5:24:59 pm
 

Lecture: Tibshirani's notes from Chapter 4 and Chapter 4 of the text

Homework: Homework03.pdf

R-code:

     Here's the code for the Wed class:  ZipCode.R

     Code for IRLS two-class logistic regression LogisticRegression.R

     Examples using glmnet including South African Heart Study used in ESL and digits 1-4 of the zip code data glmnetExamples.R

 

Example Data:

     Graphical and text output for in-class example:

          

 

     text files corresponding to the two plots above:

          Err_4var_target.txt

          Err_7var_target.txt    

 

To review matrix derivatives, check out page 8 of Stanford Professor Andrew Ng's notes:

http://www.stanford.edu/class/cs229/notes/cs229-notes1.pdf

http://stanford.edu/class/cs229/section/cs229-linalg.pdf 

 

Here's a link to paper by Friedman, Hastie, Tibshirani paper Regularization Paths for Generalized Linear Models via Coordinate Descent,  (Journal of Statistical Software, Feb 2010).  This paper describes the algorithm used in the glmnet R-package.  http://www.jstatsoft.org/v33/i01/

 

 

Here's the plot cv output from glmnet classifying characters 1-4 from the handwritten zip code data set.  damn glmnet is fast!

 

 

Comments (0)

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