Capacity and Information Efficiency of a Brain-like Associative Net

Part of Advances in Neural Information Processing Systems 7 (NIPS 1994)

Bibtex Metadata Paper


Bruce Graham, David Willshaw


We have determined the capacity and information efficiency of an associative net configured in a brain-like way with partial connec(cid:173) tivity and noisy input cues. Recall theory was used to calculate the capacity when pattern recall is achieved using a winners-take(cid:173) all strategy. Transforming the dendritic sum according to input activity and unit usage can greatly increase the capacity of the associative net under these conditions. For moderately sparse pat(cid:173) terns, maximum information efficiency is achieved with very low connectivity levels (~ 10%). This corresponds to the level of con(cid:173) nectivity commonly seen in the brain and invites speculation that the brain is connected in the most information efficient way.