Improvement of the generalization capability for a pattern-recognition neural network that uses a Gaussian-synapse neuron model

Abstract

A method for improving the generalization capability for optical pattern recognition by use of a Gaussian-synapse neuron model is discussed. By the dispersive effect of the Gaussian function the input images are blurred and then fed into a multilayer neural network for learning and recognition. The effectiveness of this method is demonstrated in two-dimensional shift- and scale-invariant optical pattern recognition.

© 2000 Optical Society of America

Neural network model for rotation invariant recognition of object shapes

Mausumi Pohit
Appl. Opt. 49(22) 4144-4151 (2010)

Neural network recognition and classification of aerosol particle distributions measured with a two-spot laser velocimeter

Eugene Yee and Jim Ho
Appl. Opt. 29(19) 2929-2938 (1990)

Optical neural network using vector-feature extraction

Yasunori Kuratomi, Akio Takimoto, Koji Akiyama, and Hisahito Ogawa
Appl. Opt. 32(29) 5750-5758 (1993)

Optically excited synapse for neural networks

Gary D. Boyd
Appl. Opt. 26(14) 2712-2719 (1987)

Neural network pattern recognition by means of differential absorption Mueller matrix spectroscopy

Arthur H. Carrieri
Appl. Opt. 38(17) 3759-3766 (1999)