Back to Search Start Over

On Symmetry and Initialization for Neural Networks

Publication Year :
2019

Abstract

This work provides an additional step in the theoretical understanding of neural networks. We consider neural networks with one hidden layer and show that when learning symmetric functions, one can choose initial conditions so that standard SGD training efficiently produces generalization guarantees. We empirically verify this and show that this does not hold when the initial conditions are chosen at random. The proof of convergence investigates the interaction between the two layers of the network. Our results highlight the importance of using symmetry in the design of neural networks.

Details

Database :
OAIster
Notes :
Nachum, Ido, Yehudayoff, Amir
Publication Type :
Electronic Resource
Accession number :
edsoai.on1228354878
Document Type :
Electronic Resource