Skip to yearly menu bar Skip to main content


Poster

On Neuronal Capacity

Pierre Baldi · Roman Vershynin

Room 517 AB #142

Keywords: [ Information Theory ] [ Learning Theory ] [ Theory ] [ Neural Coding ] [ Hardware and Systems ] [ Computational Complexity ]


Abstract:

We define the capacity of a learning machine to be the logarithm of the number (or volume) of the functions it can implement. We review known results, and derive new results, estimating the capacity of several neuronal models: linear and polynomial threshold gates, linear and polynomial threshold gates with constrained weights (binary weights, positive weights), and ReLU neurons. We also derive capacity estimates and bounds for fully recurrent networks and layered feedforward networks.

Live content is unavailable. Log in and register to view live content