Deep Learning In the News – Digest

It seems you can’t go very far these days without hearing something about Deep Learning. Here is a quick digest of some of the recent Deep Learning news and blog posts and a couple of pointers to potentially useful resources.

This compilation was made possible thanks to Lumi News AI. Articles in this digest appeared on my own personalised feed at some point in the past. I picked articles either based on recency, popularity or relevance to the context of this digest. This is not intended as a comprehensive review of deep learning.

If you are new to AI and Deep Learning, why not start with a gentle introduction into the main concepts:

Artificial Intelligence, Deep Learning, & Neural Networks Explained

“…this article is not meant to provide such a technical treatment, but rather to explain these concepts at a level that can be understood by most non-practitioners, and can also serve as a reference or review for technical folks as well…”

Read more…

…and this one:

An Introduction to Deep Learning

Includes links to open source deep learning frameworks, online courses and books.

Read more…

 


If your thirst for knowledge has not been quenched by the introductions above and you would like to have a better understanding of deep learning and related concepts, including the history of how it all came about (with a full who is who), then you may find this article a fun read:

 

Artificial Intelligence, Neural Networks, And Deep Learning (incl. TensorFlow)

“…This post is about all 3 technologies (Artificial Intelligence, Neural Networks and Deep Learning), the pioneers that led to where we are today with these technologies, where we “are” today with these technologies; along with some correlations to one of my other favorite technologies, Augmented Reality…”

Read more…

 


Some recent excitement in deep learning that made the news:

 

Machines Can Now Recognize Something After Seeing It Once

“…Oriol Vinyals, a research scientist at Google DeepMind, a U.K.-based subsidiary of Alphabet that’s focused on artificial intelligence, added a memory component to a deep-learning system—a type of large neural network that’s trained to recognize things by adjusting the sensitivity of many layers of interconnected components roughly analogous to the neurons in a brain. Such systems need to see lots of images to fine-tune the connections between these virtual neurons….”

Read more…

 

Google’s Artificial Intelligence Created Its Own Encrypted Messages

“…A team from Google Brain, the organisation’s deep learning research project, taught neural networks how to encrypt and decrypt messages. In a research paper published online the scientists created three neural networks: Alice, Bob, and Eve…”

Read more…

 


This post looks ahead to the 5th International Conference on Learning Representations and talks about papers still under review it seems:

 

Deep Learning: The Unreasonable Effectiveness Of Randomness

“…The paper submissions for ICLR 2017 in Toulon France deadline has arrived and instead of a trickle of new knowledge about Deep Learning we get a massive deluge. This is a gold mine of research that’s hot off the presses. Many papers are incremental improvements of algorithms of the state of the art. I had hoped to find more fundamental theoretical and experimental results of the nature of Deep Learning, unfortunately there were just a few. There was however 2 developments that were mind boggling and one paper that is something I’ve been suspecting for a while now and has finally been confirm to shocking results….”

Read more…

 


 

If you fancy some more technical reads:

Bayesian Deep Learning

“…Hopefully this blog post demonstrated a very powerful new inference algorithm available in PyMC3: ADVI. I also think bridging the gap between Probabilistic Programming and Deep Learning can open up many new avenues for innovation in this space, as discussed above. Specifically, a hierarchical neural network sounds pretty bad-ass…”
Read more…

 

Practicing Guide On Handling Structured & Imbalanced Datasets With Deep Learning

“While Deep Learning has shown remarkable success in the area of unstructured data like image classification, text analysis and speech recognition, there is very little literature on Deep Learning performed on structured / relational data. This investigation also focuses on applying Deep Learning on structured data because we are generally more comfortable with structured data than unstructured data….”
Read more…


 

And finally, here is a free online book on Deep Learning and KDnuggets’ introduction to TensorFlow:

Neural Networks And Deep Learning

“…The book will teach you about: 1) Neural networks, a beautiful biologically-inspired programming paradigm which enables a computer to learn from observational data, and 2) Deep learning, a powerful set of techniques for learning in neural networks…”
Read more…

 

The Gentlest Introduction To Tensorflow – Part 1

“In this series of articles, we present the gentlest introduction to Tensorflow that starts off by showing how to do linear regression for a single feature problem, and expand from there…”
Read more…

The Gentlest Introduction To Tensorflow – Part 2

“Check out the second and final part of this introductory tutorial to TensorFlow….”
Read more…


About Gabriella Kazai
Gabriella Kazai

Gabriella Kazai is VP of Data Science at Lumi, the startup company behind the Lumi Social News app which provides personalised recommendations of crowd curated content from across the world's media and social networks, see android.lumi.do. Prior to that, Gabriella worked as a research consultant at Microsoft Bing and at Microsoft Research. Her research interests include recommender systems, machine learning, IR, crowdsourcing, gamification, data mining, social networks and PIM, with influences from HCI. She holds a PhD in IR from Queen Mary University of London. She published over 90 research papers and organised several workshops (e.g., BooksOnline 2008-2012, GamifIR 2014-2015) and IR conferences (ICTIR 2009, ECIR 2015). She is one of the founders and organisers of the INEX Book Track since 2007 and the TREC Crowdsourcing track 2011-2013. She is also co-organiser of the News IR Workshop.

Leave a Reply