OpenML AutoML Benchmarking framework@ledell @open_ml https://t.co/HoBCmcdLiD
— Rachel Thomas (@math_rachel) March 11, 2019
OpenML AutoML Benchmarking framework@ledell @open_ml https://t.co/HoBCmcdLiD
— Rachel Thomas (@math_rachel) March 11, 2019
In case you missed it, Google open-sources GPipe, a library for efficiently training large deep neural networks https://t.co/6w4c7b3LEE
— Nando de Freitas (@NandoDF) March 10, 2019
Daaaamn! @Highcharts has some next-level accessibility going on with chart sonification! #dataviz https://t.co/fW4M0VK69f pic.twitter.com/IKI2jMujaT
— Mara Averick (@dataandme) March 10, 2019
Python in VS Code Adds a New Test Explorer With Auto-Discovery https://t.co/BKHLq0h2X8
— PyCoder’s Weekly (@pycoders) March 8, 2019
A fast & nice-looking PyTorch library for geometric deep learning (NN on graphs and other irregular structures).
— Yann LeCun (@ylecun) March 8, 2019
Code: https://t.co/OoOaNy9naF
Paper: https://t.co/CIzrCTqtHg
"Fast Graph Representation... https://t.co/OoOaNy9naF
Yesterday we announced TensorFlow Federated: an open framework for federated learning experiments and other computations on decentralized data. We are excited to put this framework in the hands of TensorFlow users! #TFDevSummit
— TensorFlow (@TensorFlow) March 7, 2019
More info on the blog ↓ https://t.co/azPcQ8bYh7
We are excited to share the story behind TF-Replicator, a software library that helps developers deploy their TensorFlow code between CPUs, GPUs and TPUs with minimal effort.
— DeepMind (@DeepMindAI) March 7, 2019
Blog post: https://t.co/ph73e7bIkg
Paper: https://t.co/3edo6Zetpt pic.twitter.com/y3MaWCEGGm
YES YES YES. So excited about this release!!! 🎉 https://t.co/LDBWbLKDjD
— Monica Dinculescu (@notwaldorf) March 7, 2019
We've (officially) announced the TensorFlow Privacy open source library on GitHub. Using it makes it easier to train machine-learning models with privacy. #TFDevSummit
— TensorFlow (@TensorFlow) March 7, 2019
Read the post to learn more ↓ https://t.co/xOjZHbt4pt
TF Probability now supports Keras! Check out their talk, you'll need details on this one -- but wow! pic.twitter.com/PgNVdoOeVn
— Josh Gordon (@random_forests) March 7, 2019
New tool (https://t.co/ovMLD7jpiD) argues that automatically generated text, eg. gpt2, looks real because it is "too good". Generation constraints leave behind markers that are hard for humans to detect but can be exposed to readers with statistical tests. (with @MITIBMLab) pic.twitter.com/69BkwoV9tt
— harvardnlp (@harvardnlp) March 6, 2019
TensorFlow Lite is our solution for bringing ML to mobile devices. Right now, over 2B devices have #TFLite deployed!
— TensorFlow (@TensorFlow) March 6, 2019
Tune in now and learn how to get your models up and running on mobile → https://t.co/L1MWwrvpR9 pic.twitter.com/6FoWd5ipq2