View profile

NLP News - Yann LeCun vs. Chris Manning; UMAP; Soft Cosine Measure; Convolution Visualizer; NNs on iOS Tutorial; Variational Inference Explainer; RL doesn't work; Interpretability; Neural Voice Cloning

Highlights in this edition include: Yann LeCun vs. Chris Manning; UMAP, a faster t-SNE alternative; S
NLP News
NLP News - Yann LeCun vs. Chris Manning; UMAP; Soft Cosine Measure; Convolution Visualizer; NNs on iOS Tutorial; Variational Inference Explainer; RL doesn't work; Interpretability; Neural Voice Cloning
By Sebastian Ruder • Issue #17 • View online
Highlights in this edition include: Yann LeCun vs. Chris Manning; UMAP, a faster t-SNE alternative; Soft Cosine Measure, an alternative to cosine similarity; a Convolution Visualizer; a tutorial on shipping NNs for iOS; Variational Inference explainer; RL doesn’t work yet (and why); many resources on Interpretability and Fairness; DL frameworks for NLP; Neural Voice Cloning; ad-hominem attacks; and content-based citation recommendation.

Talks and discussions
Yann LeCun and Christopher Manning discuss Deep Learning and Innate Priors
Yann LeCun and Christopher Manning discuss Deep Learning and Innate Priors
Here is a post about the main themes of the discussion.
Talk on End-to-End Differentiable Proving by Tim Rocktäschel
Talk on End-to-End Differentiable Proving by Tim Rocktäschel
Stephen Merity talks about Attention and Memory in Deep Learning
Stephen Merity talks about Attention and Memory in Deep Learning
Implementations
Uniform Manifold Approximation and Projection
Soft Cosine Measure
Tools
Tensor Comprehensions
Tutorials
How I Shipped a Neural Network on iOS with CoreML, PyTorch, and React Native
Reinforcement learning
Deep Reinforcement Learning Doesn't Work Yet
Interpretability and fairness
Interpreting machine learning models
Transparent and Interpretable AI: An interview with Percy Liang
Benchmarks and reproducibility in fair ML
Absurd and offensive dialogue agents
Absurdist Dialogues with Siri
To Give A.I. the Gift of Gab, Silicon Valley Needs to Offend You
Other blog posts and articles
Proving generalization of deep nets via compression
Twitter deleted 200,000 Russian troll tweets. Read them here.
Study Guides for Interview at AI Research Company
13 Deep Learning Frameworks for NLP in Python
Deep learning for biology
Industry insights
Neural Voice Cloning with a Few Samples
How We Built the Wine Bot Margot for Lidl using Aspect CXP
Uncommon.co launches and raises $18m to bring objectivity and efficiency to hiring
Why A.I. Researchers at Google Got Desks Next to the Boss
Paper picks
Did you enjoy this issue?
Sebastian Ruder

Get the highlights from Natural Language Processing & Machine Learning research & industry straight to your inbox every second Monday at 10am GMT.

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