Guide to Interpretable Machine Learning by @MatthewPStewart via @TDataScience

Techniques to dispel the black box myth of deep learning.

This is great and very detailed so put aside some time to read it as well as giving applause on the article.

This New Google Technique Help Us Understand How Neural Networks are Thinking by @jrdothoughts via @TDataScience

Interpretability remains one of the biggest challenges of modern deep learning applications. The recent advancements in computation models and deep learning research have enabled the creation of highly sophisticated models that can include thousands of hidden layers and tens of millions of neurons.

I found this fascinating and it is worth a read as well as a bookmark.

Google AI Blog:Predicting the Generalisation Gap in Deep Neural Networks by Yiding Jiang via @googleai

Here’s a description of a new technique that uses margin distributions to better predict a DNN’s generalization gap.

Seems a great idea to use what the Google AI team have made available in their Github is a great idea and should not be ignored. Links to a lot of sources are given thought the article.

Activation Regularisation for Reducing Generalisation Error in Deep Learning Neural Networks by/via @TeachTheMachine

This tutorial on activation regularisation for reducing generalisation error in deep learning neural networks will help you create better-learned representations and improve predictive models that make use of the learned features.

This is great and I recommend a bookmark to Jason's website as well as subscribing there. Everything he does and explains is very clear and easy to understand.

Understanding the business potential of deep learning technology by Stephen Ritter via @infomgmt

To assess the true opportunities for AI, and to distinguish the hype from the reality, one must understand this algorithm category and what makes it revolutionary.

I found this really interesting. It's always a good thing to learn a bit more about the technologies in this article.

Google’s voice-generating AI is now indistinguishable from humans by @davegershgorn via @qz

In this paper, Google researchers explain a text-to-speech system called Tacotron 2, which claims near-human accuracy at imitating audio of a person speaking from text.

This is a really exciting development and so worth keeping an eye on.

New Theory Cracks Open the Black Box of Deep Learning by Natalie Wolchover via @QuantaMagazine

Naftali Tishby is a researcher with an important new idea about how deep learning might work. He proposes that the most important part of learning is actually forgetting and his ideas about "information bottlenecks" are getting a lot of attention around the web this week.

Wow.  This makes so much sense when you think about it.

My Neural Network isn't working! What should I do? by/via @anorangeduck

11 things you probably screwed up and how to fix them.

This is a vital list of things to check and you should bookmark it so you can refer to it in the future.

App Discovery with Google Play Parts 1,2 and 3 via @googleresearch

This is a multi part blog on the Google Research Blog:

Part 1: Understanding Topics by Malay Haldar, Matt MacMahon, Neha Jha and Raj Arasu, Software Engineers

Part 2: Personalised Recommendations with Related Apps by Ananth Balashankar & Levent Koc, Software Engineers, and Norberto Guimaraes, Product Manager

Part 3: Machine Learning to Fight Spam and Abuse at Scale by Hsu-Chieh Lee, Xing Chen, Software Engineers, and Qian An, Analyst

These are great posts and this blog is well worth following.

6 areas of AI and Machine Learning to watch closely by @NathanBenaich via @kdnuggets

Artificial Intelligence is a generic term and many fields of science overlaps when comes to make an AI application. Here is an explanation of AI and its 6 major areas to be focused, going forward.

This is great and explains it in a new (to me) but very good way - well worth reading.