Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof

Details Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof

2007-05-23

arxiv.org/abs/0705.3370v1

Mathematics

Optimization and Control

22 pages

Scientific paper

We address the important theoretical question why a recurrent neural network
with fixed weights can adaptively classify time-varied signals in the presence
of additive noise and parametric perturbations. We provide a mathematical proof
assuming that unknown parameters are allowed to enter the signal nonlinearly
and the noise amplitude is sufficiently small.

Affiliated with

Also associated with

No associations

Rating

Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof 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 Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-401900