The energy landscape of a simple neural network

Abstract

We explore the energy landscape of a simple neural network. In particular, we expand upon previous work demonstrating that the empirical complexity of fitted neural networks is vastly less than a naive parameter count would suggest and that this implicit regularization is actually beneficial for generalization from fitted models.

17 pages, 15 figures

References in corpus (2)

• The Upper Bound on Knots in Neural Networks
• The empirical size of trained neural networks