Learning with recurrent neural networks / Barbara Hammer.
Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a...
Saved in:
| Online Access: |
Full Text (via Springer) |
|---|---|
| Main Author: | |
| Format: | eBook |
| Language: | English |
| Published: |
London ; New York :
Springer,
©2000.
|
| Series: | Lecture notes in control and information sciences ;
253. |
| Subjects: |
Table of Contents:
- Introduction
- Recurrent and folding networks
- Approximation ability
- Learnability
- Complexity
- Conclusion.