filters_region_cap | custom
Filter
facetapi-Q2b17qCsTdECvJIqZJgYMaGsr8vANl1n | block
Associated Lab
- Remove Branson Lab filter Branson Lab
facetapi-PV5lg7xuz68EAY8eakJzrcmwtdGEnxR0 | block
Publication Date
general_search_page-panel_pane_1 | views_panes
1 Janelia Publications
Showing 1-1 of 1 resultsYour Criteria:
11/02/17 |
Network-size independent covering number bounds for deep networks.
arXiv. 2017 Nov 02:arXiv:1711.00753
We give a covering number bound for deep learning networks that is independent of the size of the network. The key for the simple analysis is that for linear classifiers, rotating the data doesn't affect the covering number. Thus, we can ignore the rotation part of each layer's linear transformation, and get the covering number bound by concentrating on the scaling part.