View profile

Transfer learning, Chris Olah, Software 2.0, NMT with attention notebook, gradient boosting in-depth, Defense Against the Dark Arts, interpretability and bias, RL, scene understanding

Revue
 
Hi all, It feels like quite a lot has been going on in the last two weeks. Consequently, this newslet
 
June 25 · Issue #26 · View online
NLP News
Hi all,
It feels like quite a lot has been going on in the last two weeks. Consequently, this newsletter is also more packed than usual. So lean back with your beverage of choice ☕️🍵🍺 and let me take you through some of what happened in the world of ML and NLP.
Highlights  There’s been so much cool stuff, it’s hard to pick favourites. For slides and talks, my highlights are the chat with Christopher Olah about interpreting neural networks and Andrej Karpathy’s talk about Software 2.0; the NMT with attention Colaboratory notebook is pretty cool; there’s also an awesome in-depth resource about gradient boosting; two overviews of Defense Against the Dark Arts 🔮; some cool articles on interpretability and bias; articles about RL and scene understanding; and lots more articles and papers!

What's hot 🔥
Slides and talks
Machine Learning Research & Interpreting Neural Networks
Christopher D. Manning: A Neural Network Model That Can Reason (ICLR 2018 invited talk)
Deep Learning for NLP slides - Kyunghyun Cho
Building the Software 2.0 Stack by Andrej Karpathy
Modelling Natural Language, Programs, and their Intersection (NAACL 2018 Tutorial)
Efficient Deep Learning with Humans in the Loop
Tools and Implementations
Code and model for the Fine-tuned Transformer by OpenAI
Neural Machine Translation with Attention
Code for Emergent Translation in Multi-Agent Communication
NCRF++: An Open-source Neural Sequence Labeling Toolkit
Resources
How to explain gradient boosting
Tracking the Progress in Natural Language Processing
fastdeepnets Research Journal
Defense Against the Dark Arts
Defense Against the Dark Arts: An overview of adversarial example security research and future research directions
Attacks against machine learning — an overview
Interpretability and bias
Many opportunities for discrimination in deploying machine learning systems
Awesome interpretable machine learning
Bias detectives: the researchers striving to make algorithms fair
Reinforcement learning
Train a Reinforcement Learning agent to play custom levels of Sonic the Hedgehog with Transfer Learning
Metacar
Understanding scenes
Facebook open sources DensePose
Neural scene representation and rendering
More blog posts and articles
How Can Neural Network Similarity Help Us Understand Training and Generalization?
Twitter meets TensorFlow
Deep-learning-free Text and Sentence Embedding, Part 1
Deep Learning: Theory & Practice
Suicide prevention: how scientists are using artificial intelligence to help people at risk
🚀 100 Times Faster Natural Language Processing in Python
Paper picks
Improving Language Understanding by Generative Pre-Training
The Natural Language Decathlon: Multitask Learning as Question Answering
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
Did you enjoy this issue?
If you don't want these updates anymore, please unsubscribe here
If you were forwarded this newsletter and you like it, you can subscribe here
Powered by Revue