Deep Learning Weekly | Issue #76: Network Interpretability, Adversarial Examples, CV vs DL, Visual Question Anwsering

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 another week in deep learning! This week, we take a look at Microsofts new AI tool
March 12 · Issue #76 · View online
Deep Learning Weekly
Hey and welcome to another week in deep learning!
This week, we take a look at Microsofts new AI tools for Windows, compare traditional computer vision algorithms with deep learning and get to know the current state of adversarial examples.
We learn how to interpret neural networks, tackle the question if increasing depth is able to accelerate optimization and get an introduction to visual question answering. And last but not least, we found a helpful metric to estimate your models’ performance in CoreML.
Happy reading and hacking!
If you like receiving this newsletter and would like to support our work, you can do so by sharing this issue with friends and colleagues who might find it interesting. Thanks!

Microsoft wants to help developers bring their AI models to the desktop
Why Deep Learning Has Not Superseded Traditional Computer Vision
AI Has a Hallucination Problem That's Proving Tough to Fix
The Building Blocks of Interpretability
OpenAI Scholars
Can increasing depth serve to accelerate optimization?
Introduction to Visual Question Answering: Datasets, Approaches and Evaluation
Sponsored Link
Sponsor Deep Learning Weekly and reach 7348 deep learning enthusiasts.
Libraries & Code
Benchmarking Core ML — Estimating model runtimes on iOS
Sequence modeling benchmarks and temporal convolutional networks
Papers & Publications
Emergence of grid-like representations by training recurrent neural networks to perform spatial localization
Understanding Short-Horizon Bias in Stochastic Meta-Optimization
Latest Jobs
Data Scientist
Data Scientist Intern