Matching Networks for One Shot Learning · HackerPapers discussions

Matching Networks for One Shot Learning — mentioned by efferifick

Mon, 05 Dec 2016 18:19:18 GMT

Also: https://arxiv.org/abs/1606.04080

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

Matching Networks for One Shot Learning — mentioned by vonnik

Sat, 03 Dec 2016 19:37:54 GMT

[Disclosure: I work for a deep-learning company.] Robin's post reveals a couple fundamental misunderstandings. While he may be correct that, for now, many small firms should apply linear regression rather than deep learning to their limited datasets, he is wrong in his prediction of an AI bust. If it happens, it will not be for the reasons he cites. He is skeptical that deep learning and other forms of advanced AI 1) will be applicable to smaller and smaller datasets, and that 2) they will become easier to use. And yet some great research is being done that will prove him wrong on his first…

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

Matching Networks for One Shot Learning — mentioned by nl

Tue, 14 Jun 2016 16:47:11 GMT

So this is pretty interesting. One of the great hopes of the current deep learning boom is that somehow we will develop unsupervised or at least semi-supervised techniques which can perform close to the great results that are being seen with supervised learning. Adversarial Networks is one of the more likely routes to semi-supervised. There is also a lot of interesting work in combining Bayesian optimization techniques with Deep Networks to develop one-shot learning[1][2]. Some of this was (very broadly) in response to the the one-shot learning paper coming out of (I've forgotten!!) where the…

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