Orthogonal Properties of Asymmetric Neural Networks with Gabor Filters

Naohiro Ishii; Toshinori Deguchi; Masashi Kawaguchi; Hiroshi Sasaki; Tokuro Matsuo

Ayuda

Orthogonal Properties of Asymmetric Neural Networks with Gabor Filters

Naohiro Ishii ^[1] ; Toshinori Deguchi ^[2] ; Masashi Kawaguchi ^[3] ; Hiroshi Sasaki ^[4] ; Tokuro Matsuo ^[1]
1. [1] Advanced Institute of Industrial Technology
  
  Advanced Institute of Industrial Technology
  
  Japón
2. [2] National Institute of Technology, Gifu College
  
  National Institute of Technology, Gifu College
  
  Japón
3. [3] National Institute of Technology, Suzuka College
  
  National Institute of Technology, Suzuka College
  
  Japón
4. [4] Fukui University of Technology
  
  Fukui University of Technology
  
  Japón
Mostrar afiliaciones +
Localización: Hybrid Artificial Intelligent Systems. 14th International Conference, HAIS 2019: León, Spain, September 4–6, 2019. Proceedings / coord. por Hilde Pérez García, Lidia Sánchez González, Manuel Castejón Limas, Héctor Quintián Pardo, Emilio Santiago Corchado Rodríguez, 2019, ISBN 978-3-030-29858-6, págs. 589-601
Idioma: inglés
Enlaces
- Texto completo
Resumen
- Neural networks researches are developed for the recent machine learnings. To improve the performance of the neural networks, the biological inspired neural networks are often studied. Models for motion processing in the biological systems have been used, which consist of the symmetric networks with quadrature functions of Gabor filters. This paper proposes a model of the bio-inspired asymmetric neural networks, which shows excellent ability of the movement detection. The prominent features are the nonlinear characteristics as the squaring and rectification functions, which are observed in the retinal and visual cortex networks. In this paper, the proposed asymmetric network with Gabor filters and the conventional energy model are analyzed from the orthogonality characteristics. It is shown that the biological asymmetric network is effective for generating the orthogonality function using the network correlation computations. Further, the asymmetric networks with nonlinear characteristics are able to generate independent subspaces, which will be useful for the creation of features spaces and efficient computations in the learning.