Extreme Multi-Label Classification
Reminder: there is still time to submit to the Extreme Classification Workshop at ICML this year. Multi-label classification is interesting because it is a gateway drug to structured prediction. While it is possible to think about multi-label as multi-class over the power set of labels, this approach falls apart quickly unless the number of labels is small or the number of active labels per instan
Unrolled Inference
Happy New Year! My New Year's resolution is to be less afraid of non-convex optimization. Statistically there is a high likelihood that I will return to only optimizing convex losses by February :). But here's a fun paper along these lines in the meantime, Deep Fried Convnets. The idea here is to use a fast kernel approximation to replace the fully connected final layers of a deep convolutional ne
NIPS 2014
With a new venue and a deep attitude, NIPS was a blast this year, kudos to the organizers. Let's start with the “talk of the conference”. I mean this in the spirit of Time's “Man of the Year”, i.e., I'm not condoning the content, just noting that it was the most impactful. And of course the winner is ... Ilya Sutsveker's talk Sequence to Sequence Learning with Neural Networks. The swagger was jaw-
ICML 2014 Review
ICML 2014 went well, kudos to the organizers. The location (Beijing) and overlap with CVPR definitely impacted the distribution of attendees, so the conference felt different than last year. (I also learned that my blog is blocked from China, collateral damage from some kind of spat between Google and the Chinese government). Deep learning was by far the most popular conference track, to the exten
ICML 2013: Sparse, Deep, and Random
ICML 2013 was a great conference this year, kudos to the organizers. It's too big for an individual to get a comprehensive view of everything but I did notice three trends. First, sparsity as a structural constraint seemed ubiquitous. Since I know very little about this sub-field, I paid closely attention to the first two minutes of talks where foundational issues are typically (quickly!) discus
NIPS 2012 Trends
Rather than a laundry list of papers, I thought I would comment on some trends that I observed at NIPS this year. Deep Learning is BackFor the true faithful deep learning never left, but for everybody else several recent developments have coalesced in their favor. First, data sets have gotten bigger. Bigger data sets mean more complex model families can be considered without overfitting. Once data
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
NIPSplosion 2013
We can hash that
Another Random Technique
Lack of Supervision