Learning and Approximation Capabilities
✍
Lorenzo Vecci; Francesco Piazza; Aurelio Uncini
📂
Article
📅
1998
🏛
Elsevier Science
🌐
English
⚖ 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