2017

The energy landscape of a simple neural network

Gamst, Anthony Collins, Walker, Alden

Understand

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.

Built on

  • H. Jónsson, G. Mills, K. W. Jacobsen, Nudged elastic band method for finding minimum energy paths of transitions , Classical and Quantum Dynamics in Condensed Phase Simulations, Chapter 16, Ed. B. J. Berne, G. Ciccoti and D. F. Coker, 385 (World Scientific, 1998)

    1998

    Earlier work this paper cites.

Similar

Then

Nothing clear enough to list yet.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…