|
| | | | |
| | | |
| Stat |
Members: 3645
Articles: 2'506'133
Articles rated: 2609
27 April 2024 |
|
| | | | |
|
Article forum
| |
|
|
On model selection and the disability of neural networks to decompose tasks | | Marc Toussaint
; | | Date: |
19 Feb 2002 | | Journal: | Proceedings of the International Joint Conference on Neural Networks (IJCNN 2002), 245-250. | | Subject: | Adaptation and Self-Organizing Systems; Neural and Evolutionary Computing; Disordered Systems and Neural Networks | nlin.AO cond-mat.dis-nn cs.NE | | Abstract: | 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. | | Source: | arXiv, nlin.AO/0202038 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No message found in this article forum.
You have a question or message about this article?
Ask the community and write a message in the forum.
If you want to rate this article, please use the review section..
To add a message in the forum, you need to login or register first. (free): registration page
|
| |
|
|
|
|
News, job offers and information for researchers and scientists:
| |
REGISTER