Abstract
We report an experimental two-layer optical tiling network,1 the hidden layer of which grows during training. The hidden neurons are added like tiles only when they are needed. The first layer of interconnections is implemented by a dynamically refreshed photorefractive (BaTiO3) volume hologram. The hidden layer starts with a single unit, which is trained with the perceptron algorithm to classify the 2-D training inputs as well as possible. Then a second hidden neuron is added and trained to correct as well as possible classification errors that the first hidden neuron makes. This procedure is repeated until a satisfactory hidden representation of the inputs is obtained. The second layer, implemented with an optical matrix-vector multiplier, is then trained to solve the problem based on the hidden representation. A key feature of this system is the use of dynamic copying2 to control the weight decay in the photorefractive crystal as new holograms are formed.
© 1992 Optical Society of America
PDF ArticleMore Like This
Yuri Owechko
MD2 OSA Annual Meeting (FIO) 1992
Demetri Psaltis, Hsin-Yu Li, Yong Qiao, and Annette Grot
MT5 OSA Annual Meeting (FIO) 1992
B. Keith Jenkins, Armand R. Tanguay, Anupam Madhukar, and Christoph von der Malsburg
MBB1 OSA Annual Meeting (FIO) 1992