Skip to contentSkip to filters

We use cookies for analytics.

Capacity of Neural Networks for Lifelong Learning of Composable Tasks

Les Valiant

Harvard University

Recording

47 min

Abstract

Les Valiant asks how many associations a neural network can acquire in a single exposure each, retain over time, and compose later into chains. The model requires each association to activate its target while limiting unintended activity elsewhere. Bounds for random networks compare direct connections with a scheme that uses strong intermediate relays, which can substantially increase capacity and make it superlinear in network size.

Topics