Dec 18, 2016

Intuition Machine - Issue #2

By Intuition Machine • Issue #2 • View online

Welcome to the weekly newsletter covering Deep Learning Patterns, Methodology and Strategy. We’ve come up away to organize the topics to appeal to the broadest of audiences. The more general topics always are at the top, while more specialized ones are towards the bottom. We hope that this newsletter we appeal to all those interested in Deep Learning developments.

Trends

10 Deep Learning Trends and Predictions for 2017

I used to write predictions for the upcoming year in my older blog. The last one I recall writing was “Software Development Trends and Predictions for 2011”. That’s quite a long time ago. Just to…

medium.com • Share

10 Exponential Growth Trends in Deep Learning

medium.com • Share

“Predictive Learning” is the New Buzzword in Deep Learning

LeCun at NIPS 2016, has now started using the phrase “predictive learning” in substitution of “unsupervised learning”. LeCun says: This is an interesting change and indicates a subtle change in his…

medium.com • Share

AMD Enters Deep Learning Market With Instinct-Branded Accelerators And Software Stacks

Artificial intelligence, machine and deep learning are some of the hottest areas in all of high-tech today.

www.forbes.com • Share

Events

Videos at #NIPS2016, and other news and announcements

RT @Redo: Videos at #NIPS2016, and other news and announcements - Top Big Data News https://t.co/tcfC6pJne7

topdata.news • Share

50 things I learned at NIPS 2016

I learned many things about AI and machine learning at the NIPS 2016 conference. Here are a few that are particularly suited to being communicated in the space of a few sentences.

blog.ought.com • Share

Notes on NIPS 2016

ikuz.eu • Share

Strategy

How artificial intelligence could change the face of business | World Economic Forum

Artificial Intelligence (AI) may be the single most disruptive technology the world has seen since the Industrial Revolution. Granted, there is a lot of hype out there on AI, along with doomsday headlines and scary movies.

www.weforum.org • Share

Numerai Used 7,500 Faceless Coders Paid in Bitcoin to Build Its Hedge Fund's Brain | WIRED

They can’t see his data. He can’t see them. But Richard Craib believes the blind can lead the blind to a better hedge fund.

www.wired.com • Share

The Great A.I. Awakening - The New York Times

How Google used artificial intelligence to transform Google Translate, one of its more popular services — and how machine learning is poised to reinvent computing itself.

www.nytimes.com • Share

Applications

Deep Learning for Rain and Lightning Nowcasting

We describe a deep learning framework for precipitation and lightning nowcasting, applied to weather echo radar and lightning data at regional scale in Trentino-Sudtirol, in the Italian Alps.

speakerdeck.com • Share

Methodology

Nuts and Bolts of Building Deep Learning Applications

www.computervisionblog.com • Share

850k Images in 24 hours: Automating Deep Learning Dataset Creation

Normally this computer vision adventure would start with the protagonist scouring the internet to find dataset owners. These individuals have already gone through the trouble of amassing a large…

gab41.lab41.org • Share

A machine-learning system that trains itself by surfing the web

MIT researchers have designed a new machine-learning system that can learn by itself to extract text information for statistical analysis when available data is

www.kurzweilai.net • Share

GitHub - soumith/ganhacks: starter from "How to Train a GAN?" at NIPS2016

ganhacks - starter from “How to Train a GAN?” at NIPS2016

github.com • Share

Patterns

Design Patterns for Self Driving Automation

Self Driving Cars are all the rage these days. When Udacity announced a “self driving car engineering degree” a few months ago, they were…Continue reading on Intuition Machine »

medium.com • Share

Research

Swapout: Learning an Ensemble of Deep Architectures

Next up for the reading group is a paper about a new stochastic training method: Swapout.

gab41.lab41.org • Share

[1605.07571] Sequential Neural Models with Stochastic Layers

How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model.

arxiv.org • Share