Learning rules for Potts neural networks with biased patterns
D. Bollé, J. Leo van Hemmen, Jozef Huyghebaert · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · 1996
We discuss appropriate modifications of the Hebbian learning rule for Q-state Potts neural networks with biased patterns, the purpose being to prevent the storage capacity from decreasing drastically with increasing bias. Several prescriptions are compared. As an illustration their retrieval performance is studied numerically for Q=3. \textcopyright{} 1996 The American Physical Society.