https://gab41.lab41.org/flexible-image-tagging-with-fast0tag-681c6283c9b7#.tct1fx8xn

Great text about image tagging

https://github.com/facebookresearch/fastText

If you missed it, there is yet another great project for text mining

Great @addmeto channel just posted a link to https://github.com/paarthneekhara/text-to-image

This is an image generation from text. Nice example of end2end learning.

Post from FB research team: https://research.facebook.com/blog/learning-to-segment/

And direct github link: https://github.com/facebookresearch/deepmask

Facebook revealed list of universities that will receive academically support. Check if your school received one and have our congratulations. And don't hesitate to congrat your colleagues

https://research.facebook.com/blog/facebook-to-accelerate-global-ai-research-with-new-gpu-program-recipients/

How Sander Dieleman gor into Google DeepMind through Kaggle:

http://blog.kaggle.com/2016/08/29/from-kaggle-to-google-deepmind-an-interview-with-sander-dieleman/

Post about openai infrastructure for deep learning.

This is extremely rare case, because usually this information is not available and discussed publicly.

https://openai.com/blog/infrastructure-for-deep-learning/

http://www.news.cornell.edu/stories/2016/08/where-can-i-buy-chair-app-will-tell-you


Cornell University managed to release an app able to find common furniture online.

So if you see a sofa you like, you can just search for it online, to order the same in an instant.

Retailers' dream.

Apache Spark @Scale: A 60 TB+ production use case from Facebook.

https://databricks.com/blog/2016/08/31/apache-spark-scale-a-60-tb-production-use-case.html

This is next to HUGE.

Repo with PDF copy of http://www.deeplearningbook.org by Ian Goodfellow and Yoshua Bengio and Aaron Courville

https://github.com/HFTrader/DeepLearningBook

"Stacked Approximated Regression Machine: A Simple Deep Learning Approach"

https://arxiv.org/abs/1608.04062

Great article, you should definately check up

Video generation!

http://web.mit.edu/vondrick/tinyvideo/

Notes about CVPR 2016

https://gab41.lab41.org/five-things-i-learned-at-cvpr-2016-5e857c017f7b#.18bsihj9q

Flexible Image Tagging with Fast0Tag

https://gab41.lab41.org/flexible-image-tagging-with-fast0tag-681c6283c9b7#.bp7v0qdn7

And deep minds breakthrough in audio generation. It is able to generate human-like speech.

https://deepmind.com/blog/wavenet-generative-model-raw-audio/

If you know any fellow data scientists and machine learning guys, please spread the word and forward this message to them. We all work hard on providing you greatest news, so we will appreciate your attention.

How to write your first spam-filter yourself

https://blog.cambridgecoding.com/2016/01/25/implementing-your-own-spam-filter/

Two papers about using video games to train computer vision models.

And who says that video games are useless? 😏

https://arxiv.org/abs/1608.01745
https://arxiv.org/pdf/1608.01745v2.pdf

Machine learning algorithms

Language Model on One Billion Word Benchmark


In this release, we open source a model trained on the One Billion Word Benchmark (http://arxiv.org/abs/1312.3005), a large language corpus in English which was released in 2013. This dataset contains about one billion words, and has a vocabulary size of about 800K words. It contains mostly news data. Since sentences in the training set are shuffled, models can ignore the context and focus on sentence level language modeling.

In the original release and subsequent work, people have used the same test set to train models on this dataset as a standard benchmark for language modeling. Recently, we wrote an article (http://arxiv.org/abs/1602.02410) describing a model hybrid between character CNN, a large and deep LSTM, and a specific Softmax architecture which allowed us to train the best model on this dataset thus far, almost halving the best perplexity previously obtained by others.

Link for the repo: https://github.com/tensorflow/models/tree/master/lm_1b