The energy landscape of a simple neural network
| Title: | The energy landscape of a simple neural network |
|---|---|
| Authors: | Gamst, Anthony Collins, Walker, Alden |
| Publication Year: | 2017 |
| Collection: | Computer Science Statistics |
| Subject Terms: | Statistics - Machine Learning, Computer Science - Learning |
| More Details: | 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. Comment: 17 pages, 15 figures |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/1706.07101 |
| Accession Number: | edsarx.1706.07101 |
| Database: | arXiv |
Be the first to leave a comment!