← Search

Michael Mathieu

2 accepted papers

2015

The Loss Surfaces of Multilayer Networks

AISTATS 2015poster

We study the connection between the highly non-convex loss function of a simple model of the fully-connected feed-forward neural network and the Hamiltonian of the spherical spin-glass model under the assumptions of: i) variable independence, ii) redundancy in network parametrization, and iii) unifo…

Cited by 1741SourcePDFScholar