An analysis of training and generalization errors in shallow and deep networks
An open problem around deep networks is the apparent absence of over-fitting despite large over-parametrization which allows perfect fitting of the training data. In this paper, we explain this phenomenon when each unit evaluates a trigonometric polynomial. It is well understood in the theory of fun...
| Main Authors: | , |
|---|---|
| Format: | Technical Report |
| Language: | en_US |
| Published: |
Center for Brains, Minds and Machines (CBMM), arXiv.org
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/113843 |