Torch:
Twitter Cortex releases a new Autograd package, where the granularity of automatic differentiation is at the level of torch.* tensor operations.

This finer level of granularity allows one to quickly prototype new functions without worrying about writing the gradient computations as well. The autograd package is compatible with our nn framework, so the heaviest parts of your neural networks are still very fast.
https://github.com/twitter/torch-autograd

okay, if you didn't miss, there is tensorflow

A neural net - deep learning - machine learning library

Now it has a pretty interface (and it's tranding on github)

https://github.com/google/skflow

http://pixelastic.github.io/pokemonorbigdata/

Pokemon or big data

http://officialblog.yelp.com/2015/08/digesting-yelp-photos-just-got-easier-now-browse-by-category.html

Now Yelp can also classify food

http://www.theverge.com/2015/11/25/9798448/neural-network-describe-live-video-neuraltalk

This is soooo coool

Now NN can generate new faces. Just like in Matrix movie

https://m.youtube.com/watch?feature=youtu.be&v=GVe6kfJnRAw

Yan LeCunn's neural network taught itself basic arifmetic operations.

https://www.youtube.com/watch?v=4qMeVgy6CqA

Detecting Tumor Cells in Blood Samples

https://engineering.pinterest.com/blog/introducing-new-way-visually-search-pinterest

Notes of Pinterest engeneers on visual search

Direct arxiv paper link:

http://arxiv.org/abs/1505.07647

http://blogs.nvidia.com/blog/2015/11/25/compute-the-cure-3/

Deep Learning for cancer research

Finally, there is Reinforcement Learning for MOBA (games like DoTA / Heroes of the Storm / League Of Langues). It was published several months ago in Korea , which demonstrates squad of agents fight each other in league of legend like mini game. (6 layers with LSTM/MaxOut).

The mini game has two champions which have unique skill sets and attributes, which can buff/debuff targets including themselves.

So, there is a hot start for those, who want to start digging in this direction

https://onedrive.live.com/view.aspx?resid=166F2AF156F7AB19!1089&ithint=file%2cpptx&app=PowerPoint&authkey=!AA1FLzme4BNhWUE

https://www.youtube.com/watch?v=e1eTJvS_Inw

Microsoft believes that in 5 years Siri will understand human speach.

With all accents, idioms and sarcasms.

These advances may lead to new interfaces for cars, watches and even PCs. The internet of things will become something more than a concept.

http://www.businessinsider.com/microsoft-chief-scientist-xuedong-huang-on-the-future-of-speech-recognition-2015-12

Today ended a Megaface competiotion on recognition of faces.

The competition was about precision — teams had to find most similar faces.

There is a russian startup beating google — that's gonna hit every newspaper, so feel free to share this message to your friends.

Yes, you can beat a great company, even if you are in a small team.

It's not always about the size of a dog in a fight, it's about the size of a fight in a dog.

results:
http://megaface.cs.washington.edu/results/
paper:
http://arxiv.org/abs/1512.00596

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different languages. Key to our approach is our application of HPC techniques, resulting in a 7x speedup over our previous system. Because of this efficiency, experiments that previously took weeks now run in days. This enables us to iterate more quickly to identify superior architectures and algorithms. As a result, in several cases, our system is competitive with the trannoscription of human workers when benchmarked on standard datasets. Finally, using a technique called Batch Dispatch with GPUs in the data center, we show that our system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.