Computationally Efficient Radial Basis Function
| Autor: | Nitish Patel, Adedamola Wuraola |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
Computer science Gaussian 020208 electrical & electronic engineering Activation function 02 engineering and technology Square (algebra) Exponential function symbols.namesake Function approximation Radial basis function kernel 0202 electrical engineering electronic engineering information engineering symbols 020201 artificial intelligence & image processing Radial basis function Algorithm |
| Zdroj: | Neural Information Processing ISBN: 9783030041786 ICONIP (2) |
| Popis: | We introduced a Square-law based RBF kernel called SQuare RBF (SQ-RBF) which is computationally efficient and effective due to the elimination of the exponential term. In contrast to the Gaussian RBF, SQ-RBF requires smaller computational operation count and direct implementation without a call to higher order library. The derivative of the SQ-RBF is linear which will improve gradient computation and makes its applicability in multilayer perceptron neural network attractive. In experiments, SQ-RBF lead not only to faster learning but also requires significant low neurons than Gaussian RBF on networks. On an average, we recorded a speed-up in training time of about 8% for SQ-RBF based networks without affecting the overall generalizability of the network. SQ-RBF uses about 10% fewer neurons than Gaussian RBF hence making it very attractive. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|