Viewing profile — dumitrue

Apart from the captioning work already mentioned, there's also visual analogy making work by Reed et al. http://www-personal.umich.edu/~reedscot/nips2015.pdf which is pretty exciti…

But the test set has 50,000 images (across 1000 categories). It's not that easy to just "try many times" to get it right.

I don't think OpenCV really solved computer vision to be fair. There's definitely no model out there that can do image-based question & answering as well as a human can, or interpr…

Not really -- he's been an active Google+ poster even before he joined FB ( https://plus.google.com/+YannLeCunPhD/posts )

Just went out: http://arxiv.org/abs/1411.4555

Just FYI, the only additional data used by the GoogLeNet entry was from the classification challenge (aka provided by the organizers), hardly something that would make you lose sle…

The Los Angeles office is right by Venice Beach, in a beautiful setting. It's a mid-sized office (~500 employees according to http://venice.patch.com/groups/business-news/p/silicon…

Yes, though I think on public benchmarks this is still not the case. There's a dog-breed classification problem in this year's Fine-Grained challenge ( https://sites.google.com/sit…

It's actually already possible to train convolutional network-like models to distinguish between a variety of dogs, cats etc with precision that is pretty much super human. The rea…

Yes, it'd be surprised if the straightforward implementation from https://code.google.com/p/cuda-convnet/ , run on a GPU with lots of transformations, wasn't the winning entry.

It's possible that the underlying model is just not particularly good at learning from data. 11B parameters is a lot of free parameters to learn -- for instance, the main competito…

A less ugly alternative, which I much prefer, is to use multiple Chrome profiles -- keeps the worlds separate and the end-result is much cleaner!

Sending a paper for review can help with identifying whether (1) What you're solving has already been solved (2) You have a bug in your solution (3) You can get feedback from the r…

Sure, but it does depend on the field. In my field (Machine Learning) most (if not all) papers are essentially available online for free (mostly because of very strong actions like…

H1Bs can't vote you out of office so it's easy to be against them, the risk is lower to lose political capital (especially if you frame the discussion in terms of "protecting the j…

I see. Nothing gets to rattle the flame wars around here more than the combo of "is higher education really necessary or can I drop out and build the next tumblr?" and "highly-skil…

There's absolutely no requirement to have a PhD to participate in research (grad students would never get to publish, though I understand this is not what you meant). When you subm…

2 year-old story. Previous discussions: https://news.ycombinator.com/item?id=2019665 [886 days old] https://news.ycombinator.com/item?id=5503996 [46 days old]

Check this out, if you're curious about this line of thought: http://yann.lecun.com/exdb/publis/pdf/farabet-fpl-09.pdf The ImageNet winning model is a essentially glorified ConvNet…

Basically not true (anymore). If you take the model that is described by Hinton et al and apply it to some vision task for which you generated a lot of data, it will invariably wor…