Group for Research in Decision Analysis

G-90-21

Detection of Spurious States of Neural Networks

, , and

We study the complexity and propose an algorithm for the problem of determining, given p vectors of {-1, 1}n, all linear combinations of them which are also in {-1, 1}n. Computational results are reported. This problem corresponds to the detection of spurious states in Neural Networks.

, 12 pages

This cahier was revised in June 1990