Translator Disclaimer
3 May 1988 Two-Level Neural Network For Deterministic Logic Processing
Author Affiliations +
Proceedings Volume 0881, Optical Computing and Nonlinear Materials; (1988) https://doi.org/10.1117/12.944090
Event: 1988 Los Angeles Symposium: O-E/LASE '88, 1988, Los Angeles, CA, United States
Abstract
A two-level neural network is proposed for the implementation of general deterministic logic (switching) functions. The network is potentially capable of implementing any set of binary switching functions of n variables. A cascade of two neural-like processor levels gives rise to a high-performance nonlinear functional memory. The first neural layer implements a linearly separable psuedorandom mapping that maps n dimensional binary input vectors into a higher m dimensional space of randomly scattered vectors, while the second neural layer implements a one-pass associative neural memory (ANM) that maps the output of the first layer into prerecorded target vectors. The interconnection weights of this layer are synthesized using a new and highly efficient recording technique[l]. The high fan-out of the first layer mapping and the highly distributed parallel architecture of the proposed network are ideal for optical implementation.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
M H Hassoun "Two-Level Neural Network For Deterministic Logic Processing", Proc. SPIE 0881, Optical Computing and Nonlinear Materials, (3 May 1988); https://doi.org/10.1117/12.944090
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top