Deep Networks with Stochastic Depth · HackerPapers discussions

Deep Networks with Stochastic Depth — mentioned by webmaven

Sun, 30 Oct 2016 17:53:15 GMT

So far, it's "Deep Networks with Stochastic Depth": https://arxiv.org/abs/1603.09382

Paper and discussion history. A mention is not an endorsement.

Deep Networks with Stochastic Depth — mentioned by sja

Wed, 24 Aug 2016 19:17:08 GMT

Good list! I think it's important to note that this article is (intentionally) focused on modern CNN architectures, and not "deep learning" in general. I'd also add in the following "technique" articles: Geoff Hinton et al.'s dropout paper[0] and Loffe and Szegedy's Batch Normalization paper[1]. I don't think there's been enough time for the dust to settle, but I'm excited about the possibilities Stochastic Depth[2] could offer, too. [0]: http://arxiv.org/abs/1207.0580 [1]: http://arxiv.org/abs/1502.03167 [2]: http://arxiv.org/abs/1603.09382

Paper and discussion history. A mention is not an endorsement.

Deep Networks with Stochastic Depth — mentioned by karterk

Mon, 25 Apr 2016 11:22:02 GMT

Something like this? http://arxiv.org/abs/1603.09382v1

Paper and discussion history. A mention is not an endorsement.

Deep Networks with Stochastic Depth — HN submission

Mon, 04 Apr 2016 01:53:38 GMT

Deep Networks with Stochastic Depth

70 points; 8 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Networks with Stochastic Depth — HN submission

Sun, 03 Apr 2016 20:33:17 GMT

Deep Networks with Stochastic Depth

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Networks with Stochastic Depth — HN submission

Fri, 01 Apr 2016 09:28:09 GMT

Deep Networks with Stochastic Depth

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.