𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Double-exponential sigmoidal functions for neural networks

✍ Scribed by M. Heiss; S. Kampl

Publisher
Springer
Year
1997
Tongue
English
Weight
308 KB
Volume
114
Category
Article
ISSN
0932-383X

No coin nor oath required. For personal study only.

πŸ“œ SIMILAR VOLUMES

Langevin machine: a neural network based
Langevin machine: a neural network based on stochastically justifiable sigmoidal function
✍ P. S. Neelakanta; R. Sudhakar; D. DeGroff πŸ“‚ Article πŸ“… 1991 πŸ› Springer-Verlag 🌐 English βš– 700 KB

In neural networks the activation process controls the output as a nonlinear function of the input; and, this output remains bounded between limits as decided by a logistic function known as the sigmoid (S-shaped). Presently, by applying the considerations of Maxwell-Boltzmann statistics, the Langev

Polynomial Bounds for VC Dimension of Si
Polynomial Bounds for VC Dimension of Sigmoidal and General Pfaffian Neural Networks
✍ Marek Karpinski; Angus Macintyre πŸ“‚ Article πŸ“… 1997 πŸ› Elsevier Science 🌐 English βš– 438 KB

We introduce a new method for proving explicit upper bounds on the VC dimension of general functional basis networks and prove as an application, for the first time, that the VC dimension of analog neural networks with the sigmoidal activation function \_( y)=1Γ‚1+e & y is bounded by a quadratic poly

State evaluation functions and Lyapunov
State evaluation functions and Lyapunov functions for neural networks
✍ Youichi Kobuchi πŸ“‚ Article πŸ“… 1991 πŸ› Elsevier Science 🌐 English βš– 711 KB

For (I nettvork of binary State elements. consider functions from the set of State configurations into the .set of reul nurnberv. We first characterize the existenc~c of such .state evaluation f~rnctions through the properties on their difference flmctions. A method to restore the originul state elu