Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2001-07-30
Physics
Condensed Matter
Disordered Systems and Neural Networks
latex neurondlt.tex, 7 files, 6 figures, 9 pages [SPhT-T01/064], submitted to Phys. Rev. E
Scientific paper
10.1103/PhysRevE.65.016109
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.
Giraud B. G.
Touzeau A.
No associations
LandOfFree
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.
Profile ID: LFWR-SCP-O-447605