View profile

NLP News - SPINN, ∂4, Nested LSTMs, Capsule Networks, Minigo, Matrix Calculus, Past Kaggle Comps, Private Image Analysis, CNN in Google Sheets, AI & Games, IMPALA

Highlights in this edition include: lots of implementations of state-of-the-art models such as SPINN,
February 12 · Issue #16 · View online
NLP News
Highlights in this edition include: lots of implementations of state-of-the-art models such as SPINN, ∂4, Nested LSTMs, Capsule Networks, and Minigo; useful resources for learning matrix calculus or NLP and searching past Kaggle competitions; tutorials that will teach how to build a domain-specific assistant for Google Home, perform object recognition on encryted data, or train a CNN in Google Sheets; articles about RL such as different applications (trading, games, robotics) and its bias-variance trade-off; and as always exciting research papers.

Presentations and slides
The State of Natural Language Understanding
Imitation Learning for Structured Prediction in NLP
Implementations and tools
SPINN with TensorFlow eager execution
Differentiable Forth Interpreter
Nested LSTM Cell
Capsule Networks
An open-source implementation of the AlphaGoZero algorithm
mltest: Automatically test neural network models in one function call
The Matrix Calculus You Need For Deep Learning
Kaggle Past Competitions
Stanford DAWN Deep Learning Benchmark
12 of the best free Natural Language Processing and Machine Learning educational resources
Practical Deep Learning for Coders 2018
Using machine learning to build a conversational radiology assistant for Google Home
Private Image Analysis with Multi-Party Computation
Building a Deep Neural Net In Google Sheets
Limits of Deep Learning
The Shallowness of Google Translate
Greedy, Brittle, Opaque, and Shallow: The Downsides of Deep Learning
Reinforcement Learning
Introduction to Learning to Trade with Reinforcement Learning
Artificial Intelligence and Games
IMPALA: Scalable Distributed DeepRL in DMLab-30
Learning Robot Objectives from Physical Human Interaction
Making Sense of the Bias / Variance Trade-off in Reinforcement Learning
AAAI 2018 Notes
ICLR 2018 accepted papers analysis
More blog posts and articles
Requests for Research 2.0
Discovering Types for Entity Disambiguation
Three Weeks with a Chatbot and I’ve Made a New Friend
How many Mechanical Turk workers are there?
Natural and Artificial Intelligence
Industry insights
Factmata closes $1M seed round as it seeks to build an 'anti fake news' media platform
Paper picks
Personalizing Dialogue Agents: I have a dog, do you have pets too? (arXiv)
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning (ICLR 2018)
Generating Wikipedia by Summarizing Long Sequences (ICLR 2018)
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