On model selection and the disability of neural networks to decompose tasks

Details On model selection and the disability of neural networks to decompose tasks On model selection and the disability of neural networks to decompose tasks

2002-02-19

arxiv.org/abs/nlin/0202038v1

Proceedings of the International Joint Conference on Neural Networks (IJCNN 2002), 245-250.

Nonlinear Sciences

Adaptation and Self-Organizing Systems

LaTeX, 7 pages, 3 figures

Scientific paper

A neural network with fixed topology can be regarded as a parametrization of functions, which decides on the correlations between functional variations when parameters are adapted. We propose an analysis, based on a differential geometry point of view, that allows to calculate these correlations. In practise, this describes how one response is unlearned while another is trained. Concerning conventional feed-forward neural networks we find that they generically introduce strong correlations, are predisposed to forgetting, and inappropriate for task decomposition. Perspectives to solve these problems are discussed.

Affiliated with

Also associated with

No associations

Rating

On model selection and the disability of neural networks to decompose 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 On model selection and the disability of neural networks to decompose tasks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On model selection and the disability of neural networks to decompose tasks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-302913