Title
Constructive Learning Of Recurrent Neural Networks: Limitations Of Recurrent Casade Correlation And A Simple Solution
Abstract
It is often difficult to predict the optimal neural network size for a particular application. Constructive or destructive methods that add or subtract neurons, layers, connections, etc. might offer a solution to this problem. We prove that one method, recurrent cascade correlation, due to its topology, has fundamental limitations in representation and thus in its learning capabilities. It cannot represent with monotone (i.e., sigmoid) and hard-threshold activation functions certain finite state automata. We give a “preliminary" approach on how to get around these limitations by devising a simple constructive training method that adds neurons during training while still preserving the powerful fully-recurrent structure. We illustrate this approach by simulations which learn many examples of regular grammars that the recurrent cascade correlation method is unable to learn. © 1995 IEEE
Publication Date
1-1-1995
Publication Title
IEEE Transactions on Neural Networks
Volume
6
Issue
4
Number of Pages
829-836
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/72.392247
Copyright Status
Unknown
Socpus ID
0029341578 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0029341578
STARS Citation
Giles, C. Lee; Chen, Dong; and Sun, Guo Zheng, "Constructive Learning Of Recurrent Neural Networks: Limitations Of Recurrent Casade Correlation And A Simple Solution" (1995). Scopus Export 1990s. 1834.
https://stars.library.ucf.edu/scopus1990/1834