What's wrong with deep learning? (2015) [pdf]
1–8 of 8 posts
Re: What's wrong with deep learning? (2015) [pdf]
#2Here is the video.
http://techtalks.tv/talks/whats-wrong-with-deep-learning/616...
Re: What's wrong with deep learning? (2015) [pdf]
#3This was a long presentation. Yann gets to the issue in the title of the post about one third of the way through. The first third should probably be called "What's right with deep learning, or how DL works"...
For each problem, he explores some salient ideas or ways to address the issue.
TLDR:
* Theory: We don't always have good explanations for why it works.
* Reasoning: Stick a CRF on top of a Deep Net
* Memory: We need a "hippocampus". Memory networks, neural embeddings.
* Unsupervised Learning: How do we speed up inference in a generative model? Sparse autoencoders, sparse models...
For those who could use an overview of neural nets and how some of them work, this may be useful: http://deeplearning4j.org/neuralnet-overview.html
Re: What's wrong with deep learning? (2015) [pdf]
#4Here is the video. http://techtalks.tv/talks/whats-wrong-with-deep-learning/616...
Really excellent talk, thanks for posting the video! That was a dense presentation, absolutely jam packed with information and new papers and ideas. Anybody know of a 2016 version of this? I know CVPR and ICML just happened and I'm not sure their talks and presentations are up yet but this field is moving at absolutely lightning speed and I'd be interested to see updates on the techniques presented here.
Re: What's wrong with deep learning? (2015) [pdf]
#5This was a long presentation. Yann gets to the issue in the title of the post about one third of the way through. The first third should probably be called "What's right with deep learning, or how DL works"... For each problem, he explores some salient ideas or ways to address the issue. TLDR: * Theory: We don't always have good explanations for why it works. * Reasoning: Stick a CRF on top of a Deep Net * Memory: We…
A lot of 2015-2016 work can be seen as addressing the latter two. For memory, all the work on neural programming, soft and hard attention, content-addressable memory and 'memory networks'. For unsupervised learning, adversarial networks have spawned a whole bunch of papers with OpenAI's latest batch being quite exciting.
Re: What's wrong with deep learning? (2015) [pdf]
#6This was a long presentation. Yann gets to the issue in the title of the post about one third of the way through. The first third should probably be called "What's right with deep learning, or how DL works"... For each problem, he explores some salient ideas or ways to address the issue. TLDR: * Theory: We don't always have good explanations for why it works. * Reasoning: Stick a CRF on top of a Deep Net * Memory: We…
What's a crf?
Re: What's wrong with deep learning? (2015) [pdf]
#7This was a long presentation. Yann gets to the issue in the title of the post about one third of the way through. The first third should probably be called "What's right with deep learning, or how DL works"... For each problem, he explores some salient ideas or ways to address the issue. TLDR: * Theory: We don't always have good explanations for why it works. * Reasoning: Stick a CRF on top of a Deep Net * Memory: We…
What's a crf?
Conditional random field. It's a model that comes from the probabilistic/statistical side of ML, which was the "hot" ML area before deep learning.
Re: What's wrong with deep learning? (2015) [pdf]
#8Here is the video. http://techtalks.tv/talks/whats-wrong-with-deep-learning/616...
Video is not available.