Elementary Derivative Tasks and Neural Net Multiscale Analysis of Tasks

Physics – Condensed Matter – Disordered Systems and Neural Networks

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Additional info

latex neurondlt.tex, 7 files, 6 figures, 9 pages [SPhT-T01/064], submitted to Phys. Rev. E

Type

Scientific paper

Digital Object Identifier

10.1103/PhysRevE.65.016109

Abstract

Neural nets are known to be universal approximators. In particular, formal neurons implementing wavelets have been shown to build nets able to approximate any multidimensional task. Such very specialized formal neurons may be, however, difficult to obtain biologically and/or industrially. In this paper we relax the constraint of a strict ``Fourier analysis'' of tasks. Rather, we use a finite number of more realistic formal neurons implementing elementary tasks such as ``window'' or ``Mexican hat'' responses, with adjustable widths. This is shown to provide a reasonably efficient, practical and robust, multifrequency analysis. A training algorithm, optimizing the task with respect to the widths of the responses, reveals two distinct training modes. The first mode induces some of the formal neurons to become identical, hence promotes ``derivative tasks''. The other mode keeps the formal neurons distinct.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Elementary Derivative Tasks and Neural Net Multiscale Analysis of Tasks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Elementary Derivative Tasks and Neural Net Multiscale Analysis of Tasks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Elementary Derivative Tasks and Neural Net Multiscale Analysis of Tasks will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-447605

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.