Preprocessing in Attractor Neural Networks

Details Preprocessing in Attractor Neural Networks Preprocessing in Attractor Neural Networks

1995-03-17

arxiv.org/abs/cond-mat/9503101v1

Physics

Condensed Matter

to appear in Int.J.Mod.Phys.C, PostScript file

Scientific paper

Preprocessing the input patterns seems the simplest approach to invariant pattern recognition by neural networks. The Fourier transform has been proposed as an appropriate and elegant preprocessor. Nevertheless, we show in this work that the performance of this kind of preprocessor is strongly affected by the number of stored informations. This is because the phase of the Fourier transform plays a more important role than the amplitude in the recognition process.

Affiliated with

Also associated with

No associations

Rating

Preprocessing in Attractor Neural Networks 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 Preprocessing in Attractor Neural Networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Preprocessing in Attractor Neural Networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-137974