Deep Learning Weekly - 🤖 - Issue #72: Efficient ML, Learning Rates, Detectron, MobileNets v2, DeepLeague, Faster R-CNNs and more...

Hiya everyone,After this busy week, we bring you the latest and greatest articles. We start off with
January 25 · Issue #72 · View online
Deep Learning Weekly
Hiya everyone,
After this busy week, we bring you the latest and greatest articles. We start off with the top 10 problems in machine learning, explore DeepMind’s history and head right over to understanding learning rates, efficient machine learning, Faster R-CNN in depth and reprojection losses for unsupervised learning.
And as we just crossed 7000 subscribers, we would like to thank you once again for all of your support. As always, if you want to help us grow this great community of deep learning enthusiasts, simply share this issue with friends and colleagues.
See you next week!

Yann LeCun is stepping down as Facebook's head of AI research and into a new role
What are the Top 10 problems in Machine Learning for 2017?
Mustafa Suleyman: The liberal activist ensuring Google DeepMind benefits all of humanity
Understanding Learning Rates and How It Improves Performance in Deep Learning
How to do machine learning efficiently
Faster R-CNN: Down the rabbit hole of modern object detection
Reprojection Losses: Deep Learning Surpassing Classical Geometry in Computer Vision?
Speedy Neural Networks for Smart Auto-Cropping of Images
Libraries & Code
Detectron: FAIR's research platform
Deep Neuroevolution
Papers & Publications
DeepLeague: leveraging computer vision and deep learning on the League of Legends mini map
Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation
DroNet: Learning to Fly by Driving
Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
Did you enjoy this issue?
Thumbs up 1ae5a7bdfcd3220e2b376aa0c1607bc5edaba758e5dd83b482d03965219a220b Thumbs down e13779fa29e2935b47488fb8f82977fedcf689a0cc0cc3c19fa3c6bb14d1493b
Carefully curated by Deep Learning Weekly with Revue.
If you were forwarded this newsletter and you like it, you can subscribe here.
If you don't want these updates anymore, please unsubscribe here.