Automatic Design of Neural Network Structures Using AiS
| Autor: | Toshisada Mariyama, Matsumoto Wataru, Kunihiko Fukushima |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Artificial neural network
Computer science Generalization Neocognitron 02 engineering and technology Function (mathematics) computer.software_genre Network planning and design 03 medical and health sciences ComputingMethodologies_PATTERNRECOGNITION 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Radial basis function Data mining computer 030217 neurology & neurosurgery |
| Zdroj: | Neural Information Processing ISBN: 9783319466712 ICONIP (2) |
| Popis: | Structures of neural networks are usually designed by experts to fit target problems. This study proposes a method to automate small network design for a regression problem based on the Add-if-Silent AiS function used in the neocognitron. Because the original AiS is designed for image pattern recognition, this study modifies the intermediate function to be Radial Basis Function RBF. This study shows that the proposed method can determine an optimized network structure using the Bike Sharing Dataset as one case study. The generalization performance is also shown. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|