View profile

NLP News - Recurrent Highway Hypernetworks, New Multimodal Environments, LDA2vec, DL for Structured Data, NIPS highlights, AlphaZero, QAngaroo

Some highlights of this newsletter: An implementation of recurrent highway hypernetworks; new multimo
December 11 · Issue #12 · View online
NLP News
Some highlights of this newsletter: An implementation of recurrent highway hypernetworks; new multimodal environments for visual question answering; why the intelligence explosion is impossible; a tutorial on LDA2vec; Deep Learning for structured data; lots of highlights from NIPS including tutorial slides, Ali Rahimi’s presentation, debate and conversation notes, competition winners; AlphaZero; QAngaroo, a new generation of QA datasets.

When is the last time your teeth felt like they had little sweaters on them?
- A question by an Amazon Mechanical Turk worker to determine if they were talking to a human or AI (credit: Sarah Schwettmann).
Tools and implementations
mordecai - Custom-built full text and event geoparsing
The deep learning library, lessons, and tutorials
Recurrent Highway Hypernetworks
A Household multimodal environment
Realistic and Rich 3D Environments for Embodied Question Answering
pycolab game engine
Unsupervised Language Modeling at scale for robust sentiment classification
Reports on benchmarks
2017 AI Index Report
Machine learning benchmarks: Hardware providers
Your chatbot needs a personality
‘The Woebot will see you now’ — the rise of chatbot therapy
Alexa Prize winners
The promise and danger of AI
Using Artificial Intelligence to Augment Human Intelligence
The impossibility of intelligence explosion
Specifying AI safety problems in simple environments
Interpreting Deep Neural Networks with SVCCA
Debugging data: Microsoft researchers look at ways to train AI systems to reflect the real world
Translations from Turkish (a gender-neutral language) are gendered.
LDA2vec: Word Embeddings in Topic Models
Sequence Modeling with CTC
Reproducible Data Analysis in Jupyter
More blog posts and articles
1st place in Porto Seguro’s Safe Driver Prediction with representation learning
AI•ON: Artificial Intelligence Open Network
Search ICLR 2018: Top 100 papers
Artificial intelligence goes bilingual—without a dictionary
Recurrent Relational Networks
NIPS 2017
Deep Probabilistic Modelling with Gaussian Processes
Geometric deep learning on graphs and manifolds tutorial
Accepted papers of the Machine Learning for Creativity and Design workhshop
Safe and Nested Subgame Solving for Imperfect-Information Games
Ali Rahimi's Test-of-time award presentation
Machine Learning for Systems and Systems for Machine Learning
Tesla's conversation on AI with Andrej Karpathy, Elon Musk, and others
Interpretability debate
Winning system white paper
Highlights of the Teaching AI to Run competition at NIPS 2017
Industry insights
Facebook AI Research Residency Program
Victims of Sexual Harassment Have a New Resource: AI
How Reuters’s Revolutionary AI System Gathers Global News
Facebook to expand artificial intelligence to help prevent suicide
Paper picks
Are GANs Created Equal? A Large-Scale Study
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
Ethical Challenges in Data-driven Dialogue Systems
Neural Text Generation: A Practical Guide
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Dataset spotlight
QAngaroo - Reading Comprehension with Multiple Hops
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