dc.contributor.author | Poggio, Tomaso | |
dc.contributor.author | Liao, Qianli | |
dc.date.accessioned | 2020-08-18T19:56:06Z | |
dc.date.available | 2020-08-18T19:56:06Z | |
dc.date.issued | 2020-08-17 | |
dc.identifier.uri | https://hdl.handle.net/1721.1/126653 | |
dc.description.abstract | Square loss has been observed to perform well in classification tasks, at least as well as crossentropy. However, a theoretical justification is lacking. Here we develop a theoretical analysis for the square loss that also complements the existing asymptotic analysis for the exponential loss. | en_US |
dc.description.sponsorship | This material is based upon work supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF-1231216. | en_US |
dc.publisher | Center for Brains, Minds and Machines (CBMM) | en_US |
dc.relation.ispartofseries | CBMM Memo;112 | |
dc.title | Implicit dynamic regularization in deep networks | en_US |
dc.type | Technical Report | en_US |
dc.type | Working Paper | en_US |
dc.type | Other | en_US |