An optimal method for linear threshold neural network synthesis

In the digital design area the minimized function of binary variables may be represented by two levels of AND/OR gates. However, depending upon the application, the design may require a large number of gates. We propose a method that is capable of reducing the required number of gates necessary to realize an N-dim binary function by implementing linear threshold units. Hence, we propose an approach for obtaining a minimal linear threshold neural network from a binary pattern space. The method is based on optimal groupings of minimal-sum-of-product (MSP) terms of a function represented by binary class patterns. In doing so, we are able to obtain a fast realization of a linear threshold neural network. Several experimental results are given.