Home /  Workshop /  Schedules /  Deriving neural circuits from first principles

Deriving neural circuits from first principles

Theory of Neural Computation October 05, 2015 - October 07, 2015

October 05, 2015 (03:15 PM PDT - 04:30 PM PDT)
Speaker(s): Mitya Chklovskii (Simons Foundation)
Location: SLMath: Eisenbud Auditorium
Tags/Keywords

  • online principal component analysis

  • matrix factorization

  • large-scale neural modelling

  • dimension reduction

Primary Mathematics Subject Classification
Secondary Mathematics Subject Classification No Secondary AMS MSC
Video

14357
Abstract

Inspired by experimental neuroscience results we developed a family of online algorithms that reduce dimensionality, cluster and discover features in streaming data. The novelty of our approach is in starting with similarity matching objective functions used offline in Multidimensional Scaling and Symmetric Nonnegative Matrix Factorization. We derived online distributed algorithms that can be implemented by biological neural networks resembling brain circuits. Such algorithms may also be used for Big Data applications.
Supplements
24728?type=thumb Chklovskii 1.4 MB application/pdf Download
Video/Audio Files

14357

H.264 Video 14357.mp4 434 MB video/mp4 rtsp://videos.msri.org/data/000/024/367/original/14357.mp4 Download
Troubles with video?

Please report video problems to itsupport@slmath.org.

See more of our Streaming videos on our main VMath Videos page.