In the News
The Mobile Internet is over. Baidu goes all in on AI
Baidu spent $2.9M on AI over 2 years, has 1300 AI researchers
Out of road: driverless vehicles are replacing the trucker
New self-driving technology threatens an American way of life
Sponsor
Meet industry leaders, startups, data scientists & CTOs leading the deep learning revolution
The summit will showcase the opportunities of advancing methods in deep learning and their impact across healthcare & medicine. Confirmed speakers include: BioBeats, Philips Research, MIT and more. The Deep Learning Summit will be running alongside, meaning you can enjoy additional sessions and networking opportunities with leading innovators and professionals.
Learning
Machines could learn common sense from video
Yann LeCun says the next frontier in machine vision is software that learns just by observing the world.
How DeepMind’s memory trick helps AI learn faster
"While AI systems can match many human capabilities, they take 10 times longer to learn. Now, by copying the way the brain works, Google DeepMind has built a machine that is closing the gap."
Enabling Continual Learning in Neural Networks
"Computer programs that learn to perform tasks also typically forget them very quickly. We show that the learning rule can be modified so that a program can remember old tasks when learning a new one. This is an important step towards more intelligent programs that are able to learn progressively and adaptively."
Apple’s AI Director: Here’s how to supercharge Deep Learning
Ruslan Salakhutdinov, who leads Apple’s AI efforts, says emerging techniques could make the most popular approach in the field far more powerful.
Software tools & code
Basics of Entity Resolution
Entity resolution (ER) is the task of disambiguating records that correspond to real world entities across and within datasets. The applications of entity resolution are tremendous, particularly for public sector and federal datasets related to health, transportation, finance, law enforcement, and antiterrorism.
Deep Learning without Backpropagation
In this blogpost, we're going to prototype (from scratch) and learn the intuitions behind DeepMind's recently proposed Decoupled Neural Interfaces Using Synthetic Gradients paper.
Encrypted Deep Learning
Using so-called homomorphic encryption to run Deep Learning models on encrypted data.
Upgrade to SyntaxNet, new models and a parsing competition
"We are releasing a major upgrade to SyntaxNet. This upgrade incorporates nearly a year’s worth of our research on multilingual language understanding, and is available to anyone interested in building systems for processing and understanding text"
Deep Learning reinvents the hearing aid
Finally, wearers of hearing aids can pick out a voice in a crowded room
Hardware
In-depth look at Google’s TPU architecture
Google revealed some details on its TPU architecture to train and run Deep Learning models. Google says the TPU runs 15-30 times faster than conventional GPUs.
Some thoughts
About
This newsletter is a collection of AI news and resources curated by @dlissmyr. If you find it worthwhile, please forward to your friends and colleagues, or share on your favorite network!
Share on Twitter · Share on Linkedin · Share on Google+
Suggestions or comments are more than welcome, just reply to this email.
Thanks!