Abstract
A basic feature of the optical neural networks (or neurooptic processors1) being developed by Northrop is that each optical synapse is identified uniquely with a single-volume holographic phase grating of grating vector K. These optical synapses occupy a single-point vicinity in Fourier space (Kx,Ky,Kz), while their biological counterparts occupy a single-point vicinity in configuration space (x,y,z). This type of neurooptic architecture evokes a number of problems fundamental to real time high-throughput optical processing. In this paper we address ourselves specifically to the problem of executing adaptive neural network algorithms using multiple-exposure Bragg holography.
© 1986 Optical Society of America
PDF ArticleMore Like This
Tomasz Jannson, C. Karaguleff, and H. M. Stoll
WG32 OSA Annual Meeting (FIO) 1986
John Hong
MK2 OSA Annual Meeting (FIO) 1991
H. M. Stoll, T. Jannson, and C. Karaguleff
MDD4 OSA Annual Meeting (FIO) 1986