A New Proposition of the Activation Function for Significant Improvement of Neural Networks Performance
| Autor: | Jarosław Bilski, Alexander I. Galushkin |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Artificial neural network
Computer science Activation function Hyperbolic function 02 engineering and technology Function (mathematics) Transfer function Nonlinear system Simple (abstract algebra) 020204 information systems 0202 electrical engineering electronic engineering information engineering Artificial neuron 020201 artificial intelligence & image processing Algorithm |
| Zdroj: | Artificial Intelligence and Soft Computing ISBN: 9783319393773 ICAISC (1) |
| DOI: | 10.1007/978-3-319-39378-0_4 |
| Popis: | An activation function is a very important part of an artificial neuron model. Multilayer neural networks can properly work only when these functions are nonlinear. A simple approximation of an often applied hyperbolic tangent activation function is presented. This proposed function is computationally highly effective. Computational comparisons for two well-known test problems are discussed. The results are very promising in potential applications to FPGA chips designing. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|