Deep Learning Weekly | Issue #66: Parallel WaveNet, Capsule Networks, Creativity meets AI, Satellites images, line counting

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, this week we bring you an update to the WaveNet architecture, reports on a satellite image
November 26 · Issue #66 · View online
Deep Learning Weekly
Hey Folks,
We take a deep dive into the reasoning behind capsule networks, learn how to quickly categorize new papers, look at a discussion on licensing network weights and learn to count the line in front of our favorite burger shop. Furthermore, we found a way to run TensorFlow with CUDA on MacOS and investigate network training on mobile devices.
Happy hacking and reading. As always if you enjoy receiving this newsletter you can help us by sharing it with friends and colleagues.
See you next week!

High-fidelity speech synthesis with WaveNet
Wanted: AI That Can Spy
AWS ramps up in AI with new consultancy services and Rekognition features
When Creativity meets A.I.
Artificial Intelligence Can Hunt Down Missile Sites in China Hundreds of Times Faster Than Humans
Uncovering the Intuition behind Capsule Networks and Inverse Graphics
Expressivity, Trainability, and Generalization in Machine Learning
Do the weights trained from a dataset also come under the same license terms as the dataset?
Counting Crowds and Lines
Libraries & Code
Installing TensorFlow 1.4.0 on macOS with CUDA support
Training on the device
Papers & Publications
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Coupled Ensembles of Neural Networks