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.
[1]
M H. Hassoun,et al.
New Recording Algorithm For Hopfield Model Associative Memories
,
1988,
Photonics West - Lasers and Applications in Science and Engineering.
[2]
Robert O. Winder,et al.
Threshold logic
,
1971,
IEEE Spectrum.
[3]
J. Orbach.
Principles of Neurodynamics. Perceptrons and the Theory of Brain Mechanisms.
,
1962
.
[4]
J. Taylor,et al.
Switching and finite automata theory, 2nd ed.
,
1980,
Proceedings of the IEEE.
[5]
A. Mullin.
Threshold Logic: A Synthesis Approach (Michael L. Dertouzos)
,
1966
.