Home >> Education >> Access Grid >> Events and Seminars >> Approximating cross-validation results for binary classification methods preceded by principal component dimension reduction
Approximating cross-validation results for binary classification methods preceded by principal component dimension reduction PDF print email

Host Institution:

La Trobe University, AGR Room.

Title of Seminar:

Approximating cross-validation results for binary classification methods preceded by principal component dimension reduction

Speaker's Name:

Mitra Jazayeri

Speaker's Institution:

La Trobe University

Time and Date:

2:00pm Friday 9 May 2008

Seminar Abstract:

I will be discussing the study of dimension reduction of high dimensional data for binomial response variable data sets when the number of individuals sampled is less than the number of measurement variables. The application of principle component analysis as a prestep to Sliced Inverse Regression and Sliced Average Variance Estimation will be presented. In this setting in order to produce an efficient algorithm, an approximation technique using first and second order perturbations is suggested as a one step eigen-analysis in the cross-validation step of the classification of the binomial response variable data sets.

Seminar Convenor:

This e-mail address is being protected from spambots. You need JavaScript enabled to view it

AGR IT support:

This e-mail address is being protected from spambots. You need JavaScript enabled to view it

 

Message to parents:
There have been recent reports in the media regarding high-pressure techniques used in the marketing and sale of computer based mathematics learning systems. The Australian Mathematical Sciences Institute (AMSI) is not in any way associated, connected or affiliated with companies or organisations involved in these activities, and does not endorse or vouch for such products in any way. Please see Consumer Affairs Victoria newletter, March 2008 "Parents warned about aggressive software sales."