[Haifux] [HAIFUX LECTURE] Towards One-Class Pattern Recognition in Brain Activity via Neural Networks

Eli Billauer eli at billauer.co.il
Sun Apr 11 13:39:58 MSD 2010

On Monday, April 12th (TOMORROW) at 18:30, Haifux will gather to hear 
Omer Boehm  talk about

         Towards One-Class Pattern Recognition in Brain Activity via 
Neural Networks


I would like to present the work done regarding how one-class 
recognition of cognitive brain functions across multiple subjects can be 
performed at the 90% level of accuracy via an appropriate choices of 
features which can be chosen automatically. This work extends one class 
work done by Larry Manevitz (Haifa University) and David Hardoon (UCL) 
who showed that such classification was first shown to be possible in 
principle albeit with an accuracy of about 60%. It also is comparable to 
work of various groups around the world e.g. Michell et al which have 
concentrated on two-class classification. The importance of this work is 
that one class is often the appropriate classification setting for 
identifying cognitive brain functions. The methodologies for one class 
classification used in this paper are the compression neural network for 
one class classification, a wrapper approach and the genetic algorithm 
for feature selection. In addition, versions of one-class SVM due to 
were investigated.


We meet in Taub (CS Faculty) building, room 6. For instructions see:

Attendance is free, and you are all invited!


Future Haifux events include:

26/04/10 Making the Internet Accessible: Workshop hosted by Orr Dunkelman
07/06/10 The Ben Yehuda Project Software

(The gap between the lectures is intended for YOU to lecture about 
something interesting!)


We are always interested in hearing your talks and ideas. If you wish to 
give a talk, hold a discussion, or just plan some event haifux might be 
interested in, please contact us at webmaster at haifux.org

Web: http://www.billauer.co.il

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://haifux.org/pipermail/haifux/attachments/20100411/b1d6f6d7/attachment.html 

More information about the Haifux mailing list