Day 51: Glow

Well here goes. Our ICML Debates paper is live: "Troubling Trends in Machine Learning Scholarship". If anyone needs me, I'll be in witness protection. 🙄 https://t.co/ziPWyhvwKP

— Zachary Lipton (@zacharylipton) July 9, 2018

Google Cloud Platform now provides prepackaged VM images for @TensorFlow and @PyTorch that work with Cloud GPUs out of the box. Still in beta, please give any feedback to @b0noi! https://t.co/0h1R5va1z0 pic.twitter.com/yU4pf9CCjs

— hardmaru (@hardmaru) July 10, 2018

Dask development status update:https://t.co/NikcIo26D4

Yarn, incremental machine learning, and more examples pic.twitter.com/tftfaWnqVN

— Dask (@dask_dev) July 9, 2018

dlib 19.14 is out. Pushed more stuff into the Python API. Also added a simple auto-ML tool for training binary classifiers. See for details: https://t.co/YpXr6h04xg

— Davis King (@nulhom) July 7, 2018

Nice discussion on Cross Validated of equivalence and non-equivalence of confidence intervals and Bayesian credible intervals when the prior is restricted: https://t.co/I4udu0mZMN

— Frank Harrell (@f2harrell) July 9, 2018

New #nlproc blog post: "Design Patterns for Production NLP Systems" https://t.co/m4a4MYgtfT pic.twitter.com/GUdydhnHVy

— Delip Rao (@deliprao) July 9, 2018

Data science glossary on @kaggle - a great curated list of kernels providing forkable and reproducible tutorials on machine learning algorithms https://t.co/Anbd8lFMg1

— Ben Hamner (@benhamner) July 9, 2018

Btw - this isn't a static, manually curated list. It's generated in Python on kernel tags, votes, and other metadata in a public Kaggle data release (updated daily). Expand the code sections in the notebook to see the source https://t.co/UEajPWWYVu

— Ben Hamner (@benhamner) July 10, 2018

A Tour of Reinforcement Learning: The View from Continuous Control. A nice review paper, and a summary of @BeenWrekt's views of the RL field from his series of recent blog posts. https://t.co/ViCPPruced

— hardmaru (@hardmaru) July 10, 2018

Model AI Assignments https://t.co/twAot7jT4J - This is a neat collection of assignments/exercises to learn about various Machine Learning techniques

— Denny Britz (@dennybritz) July 10, 2018

A mechanistic model of connector hubs, modularity, and cognition
“model of hub connectivity accurately predicts the cognitive performance of 476 individuals in four distinct tasks”

https://t.co/IZE1Pihies pic.twitter.com/eEdqOXjz0w

— Alessandro Vespignani (@alexvespi) July 9, 2018

Synthesizing realistic high-resolution images with Glow, a new reversible generative model: https://t.co/WIa9aI6NGU pic.twitter.com/vdCruz17li

— OpenAI (@OpenAI) July 9, 2018

Go check out our interactive demo and upload your face to make it smile, grow old, add a beard, get blonde hair! Wonder how Prof. Hinton looks with a beard... pic.twitter.com/ydAVCZIK3s

— Prafulla Dhariwal (@prafdhar) July 9, 2018

Feature-wise transformations - A new Distill article by @dumoulinv, Ethan Perez, @nschucher, Florian Strub, @harm_devries, Aaron Courville, Yoshua Bengiohttps://t.co/YH4wHHs0X4

— distillpub (@distillpub) July 9, 2018

Lake nerds: Had to try it 👌 https://t.co/jed9tjyFPj @Brideau @dataandme pic.twitter.com/SoKpUABenR

— Hilary Dugan (@hildug) July 9, 2018

🍾 I'm glad to announce a new #dataviz project:

--> https://t.co/KLihruhSJr

A classification of chart types based on data input format. Includes a lot of #rstat code, a poster for @useR2018_conf , a gallery of caveats, and plenty of tips and tricks! pic.twitter.com/0TJctwitOI

— Yan Holtz (@R_Graph_Gallery) July 9, 2018

Plotly's new #Python interface: fast rendering of huge datasets, interactive #Jupyter notebooks, validation… This is huge! https://t.co/iRzERrUdQX by @jonmmease 👍 pic.twitter.com/VvnGdmgGEk

— Radim Řehůřek (@RadimRehurek) July 6, 2018

Generally fun and the first table seems like a good reminder that the minimizer of L2 approximation is usually not also the L∞ minimizer: https://t.co/ohjvusrMDG

— John Myles White (@johnmyleswhite) July 9, 2018