pith. sign in

arxiv: 1807.06630 · v1 · pith:DPHVMIS5new · submitted 2018-07-17 · 💻 cs.LG · stat.ML

Expressive power of outer product manifolds on feed-forward neural networks

classification 💻 cs.LG stat.ML
keywords networksnetworkneuraloriginaltrainingevenexpressivefeedforward
0
0 comments X
read the original abstract

Hierarchical neural networks are exponentially more efficient than their corresponding "shallow" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. Our main idea is to mathematically understand and describe the hierarchical structure of feedforward neural networks by reparametrization invariant Riemannian metrics. By computing or approximating the tangent subspace, we better utilize the original network via sparse representations that enables switching to shallow networks after a very early training stage. Our experiments show that the proposed approximation of the metric improves and sometimes even surpasses the achievable performance of the original network significantly even after a few epochs of training the original feedforward network.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.