Deep Learning Weekly | Issue #70: Hardware Limbo, Neuroevolution, Googles Strategy, Adversarial Spheres, Panoptic Segmentation

Bringing you everything new and exciting in the world of
 deep learning from academia to the grubby depth
 of industry every week right to your inbox. Free.

Hey Folks! We're starting off the new year with a look at the hardware limbo building up on the horiz
January 11 · Issue #70 · View online
Deep Learning Weekly
Hey Folks!
We’re starting off the new year with a look at the hardware limbo building up on the horizon, analyze Google’s AI strategy and dream about intelligent laundry robots. We learn about neuroevolution and the history of math, take a look at the best-rated machine learning projects of 2018 and an impressive new house dataset was made available.
In academia, Ian Goodfellow et al. released a new paper on adversarial examples, Facebook outlined the holy grail of all segmentation tasks, panoptic segmentation, and now that RNNs can read, we are teaching them to skim as well.
As always, we hope you’ll enjoy reading as much as we did and would appreciate you sharing this newsletter with friends and colleagues.
See you next week!

Deep Learning Hardware Limbo
AI in 2018: Google seeks to turn early focus on AI into cash
This $16,000 robot uses artificial intelligence to sort and fold laundry
Gradient descent vs. neuroevolution
30 Amazing Machine Learning Projects for the Past Year
From deep learning down
Libraries & Code
facebookresearch/House3D: a Realistic and Rich 3D Environment
Release of TensorFlow 1.5.0
dlib C++ Library: A Global Optimization Algorithm Worth Using
Papers & Publications
Adversarial Spheres
Panoptic Segmentation
Neural Speed Reading via Skim-RNN