On Neuronal Capacity
Pierre Baldi · Roman Vershynin
Keywords:
Information Theory
Learning Theory
Theory
Neural Coding
Hardware and Systems
Computational Complexity
2018 Poster
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.
Chat is not available.
Successful Page Load