Domains of attraction in neural networks

Thomas B. Kepler , L.F. Abbott

The domain of attraction of a neural network memory fixed point is computed as a function of its local magnetic fields. When combined with standard learning algorithms, the result makes it possible to construct saturated associative networks memories with precisely specified recall properties.

Keywords: content addressable storage; learning systems; neural nets

Domains: Physics archives

Thomas B. Kepler, L.F. Abbott. Domains of attraction in neural networks. Journal de Physique, 1988, 49 (10), pp.1657-1662. ⟨10.1051/jphys:0198800490100165700⟩. ⟨jpa-00210846⟩