Dynamical neural network architecture for continuous learning (Q2770461)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1703381
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Dynamical neural network architecture for continuous learning |
scientific article; zbMATH DE number 1703381 |
Statements
10 February 2002
0 references
neural network
0 references
continuous learning
0 references
algorithm ICE
0 references
Dynamical neural network architecture for continuous learning (English)
0 references
An incremental construction algorithm ICE for continuous learning tasks for neural network is developed. The main advantages of the ICE-algorithm are: 1) the number of RBF-neurons and the number of local models of the hybrid network have not to be determined in advance (an important feature for fast initial learning); 2) the ability to simultaneously learn the target function and a confidence value for the network output. Finally a special version of the ICE-algorithm with asymmetric receptive fields is introduced. Similarities to fuzzy logic are intended.
0 references
0.7399017214775085
0 references
0.7383285760879517
0 references
0.7261636257171631
0 references
