Deep Learning Weekly | Issue #74: Cloud Service Comparison, TPUs, Quantum Computing, Issues of deep RL, Pruning, DensePose

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 and welcome to a new week in deep learning! This week, we bring you a mega-benchmark across cloud
February 15 · Issue #74 · View online
Deep Learning Weekly
Hey and welcome to a new week in deep learning!
This week, we bring you a mega-benchmark across cloud GPU services, Googles now available TPUs, a look at quantum computing and an article on all the discussions around artificial intelligence. We continue our Deep Learning In The Wild series with, a startup from Munich delivering tailored AI solutions.
Afterwards, we dive deep into the current issues of deep reinforcement learning, learn all the matrix calculus needed in deep learning, how pruning actually works, what it takes to use DL in an iOS app and learn about an alternative to eyeballing a learning rate schedule.
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!

Machine learning mega-benchmark: GPU providers
Cloud TPU machine learning accelerators now available in beta
Quantum Algorithm Will Push AI 'Thinking' to New Heights
Asking the Right Questions About AI
Deep Learning in the Wild is a series on, where we interview companies and startups across industries to find out how deep learning is actually applied to tackle real-world problems. - Bespoke AI solutions
Deep Reinforcement Learning Doesn't Work Yet
The Matrix Calculus You Need For Deep Learning
Pruning Neural Networks: Two Recent Papers
Libraries & Code
How I Shipped a Neural Network on iOS with CoreML, PyTorch, and React Native
Automatic Learning Rate Scheduling That Really Works
Papers & Publications
IMPALA: Scalable Distributed DeepRL in DMLab-30
SMASH: One-Shot Model Architecture Search through HyperNetworks
Face Destylization
Efficient Neural Architecture Search via Parameters Sharing