Deep Learning Weekly - 🤖 - Issue #44: AI Understanding, Google MobileNet, Machine Intelligence Summits, Sobolev Trainings for NNs, Flag-planting and overselling results

Revue
 
Welcome to another week in deep learning,this week we bring you a discussion of problems stemming fro
 
June 17 - Issue #44 - View online
Deep Learning Weekly
Welcome to another week in deep learning,
this week we bring you a discussion of problems stemming from fast publishing cycles and flag planting on arxiv.org, an explanation of the difference between classical AI and deep learning through an epistemological lens, 20% off two REWORK machine intelligence conferences and fascinating new research on exploiting the derivate of your target function.

Happy reading and hacking.

As always if you enjoy receiving this newsletter you can help us out by sharing it with friends, family, and colleagues. :)

Industry
An Exclusive Look at How AI and Machine Learning Work at Apple
SoftBank Agrees to Buy Robot Maker Boston Dynamics From Google Parent Alphabet
Learning
Discussion: An Adversarial Review of “Adversarial Generation of Natural Language”
Why AI Works – Artificial Understanding
Google Research: MobileNets: Open-Source Models for Efficient On-Device Vision
Cheatsheets AI: Essential Cheat Sheets for deep learning and machine learning researchers
Counting Objects with Faster R-CNN
Events & Conferences
RE•WORK Machine Intelligence Summit Amsterdam
RE•WORK Machine Intelligence in Autonomous Vehicles Summit Amsterdam
Libraries & Code
ml4a/ml4a-ofx ¡ GitHub
Pytorch implementation of "A simple neural network module for relational reasoning"
Code for MobileNets: Open-Source Models for Efficient On-Device Vision
Papers & Publications
Sobolev Training for Neural Networks
Variational Approaches for Auto-Encoding Generative Adversarial Networks
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour – Facebook Research
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.