𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Universal approximation capability of EBF neural networks with arbitrary activation functions

✍ Scribed by Tianping Chen; Hong Chen


Book ID
112494926
Publisher
Springer
Year
1996
Tongue
English
Weight
546 KB
Volume
15
Category
Article
ISSN
0278-081X

No coin nor oath required. For personal study only.


πŸ“œ SIMILAR VOLUMES


Learning and Approximation Capabilities
✍ Lorenzo Vecci; Francesco Piazza; Aurelio Uncini πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 297 KB

In this paper, we study the theoretical properties of a new kind of artificial neural network, which is able to adapt its activation functions by varying the control points of a Catmull-Rom cubic spline. Most of all, we are interested in generalization capability, and we can show that our architectu