Some new results on the capabilities of integer weights neural networks in classification problems

This paper analyzes some aspects of the computational power of neural networks (NN) using integer weights in a very restricted range. Using limited range integer values opens the road for efficient VLSI implementations because: 1) a limited range for the weights can be translated into reduced storage requirements, and 2) integer computation can be implemented in a more efficient way than the floating point one. The paper shows that a neural network using integer weights in the range [-p,p] (where p is a small integer value) can classify correctly any set of patterns included in a hypercube of unit side length centered around the origin of R_n, n⩾2, for which the minimum Euclidean distance between two patterns of opposite classes is d_min ⩾√(n-1)/2p