Results on the Steepness in Backpropagation Neural Networks
| Type of publication: | Conference paper |
| Citation: | Moerland-94.1 |
| Booktitle: | Proceedings of the '94 SIPAR-Workshop on Parallel and Distributed Computing |
| Year: | 1994 |
| Month: | 10 |
| Organization: | SI Group for Parallel Systems |
| Address: | Institute of Informatics, University P\'erolles, Fribourg, Switzerland |
| Abstract: | The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the steepness of its activation functions is investigated. In specific, it is discussed that changing the steepness of the activation function is equivalent to changing the learning rate and the weights. Some applications of this result to optical and other hardware implementations of neural networks are given. |
| Userfields: | ipdmembership={neuron learning}, |
| Keywords: | (adaptive) learning rate, activation function, adaptive steepness, backpropagation, bias, connectionism, gain, initial weight, multilayer neural network, neural computation, neural computing, neural network, neurocomputing, optical implementation, sigmoid steepness, slope |
| Projects |
Idiap |
| Authors | |
| Editors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|