Top news of the week: 04.06.2020.
#GPU #ProTip #icml20 #gml #icml #icml2020
Research
"If you want to learn deep learning by example, from a team that has seemingly written the book on it, Deep Learning for Coders with fastai and PyTorch is for you."
Thanks @mattmayo13 @kdnuggets! 😊
https://t.co/K3d64GStXc
OpenDeep Learning for Coders with fastai and PyTorch: The Free eBook
If you are interested in a top-down, example-driven book on deep learning, check out the draft of the upcoming Deep Learning for Coders with fastai & PyTorch from fast.ai team.
RT @RisingSayak: Super excited to share my conversation with @nikiparmar09, Senior Research Scientist at Google Brain:
https://t.co/pg4QJWrEsU.
We talk about Niki's motivations to pursue Machine Learning, the kind of problems she works on, her approach towards conducting research, and more.
OpenAn interview with Niki Parmar, Senior Research Scientist at Google Brain
I am pleased to have Niki Parmar for today’s interview. Niki is a Senior Research Scientist at Google Brain where she is involved in…
RT @rapidsai: Our new #GPU-based SubWord Tokenizer in @rapidsai CLX feeds BERT models 270x faster than other wordpiece tokenizers. Supports non-truncation of logs and stride, and pipes directly to @PyTorch. Give it a shot! https://t.co/DPe4TpMzYq
OpenPreprocess Your Data at Lightspeed with Our GPU-based Tokenizer for BERT Language Models
This tokenizer, applied as a pre-processing step before input into a BERT language model, runs up to 270x faster than CPU implementations
RT @jasonsalas: #ProTip: here's my gotchas for any TinyML newbies having trouble getting the super-cool demos of running machine learning on a microcontroller in @petewarden & @dansitu's book. (Which is 🌟🌟🌟🌟🌟excellent.)
https://t.co/gK2GnOoZ7n
OpenGotchas to getting the TinyML book demos to run
I’ve been having tremendous fun working with the demos for TinyML book, written by Pete Warden and Daniel Situnayake about the insanely…
DeepMind Surges on, Releasing Acme and Reverb RL Libraries @DeepMind @mw_hoffman @bshahr @john_aslanides @gbarthmaron @FeryalMP @katebaumli @koraykv https://t.co/w2apaktzvf
OpenDeepMind Surges on, Releasing Acme and Reverb RL Libraries
DeepMind, an Alphabet subsidiary, continues to pump out useful software libraries for the machine learning research community. It just released Acme, an RL agent trainer, and Reverb, an RL ...
RT @SergeyI49013776: ICML 2020 papers are out (https://t.co/CSYW7rQu7G) and here are some quick stats:
• 4990 submissions (vs 3424 in 2019)
• 1088 accepted (vs 774 in 2019)
• 21.8% acceptance rate (vs 22.6% in 2019)
• 53 graph papers (5% of total)
#icml #icml2020 #icml20 #gml
Open
Reverb
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research - deepmind/reverb
RT @chrmanning: The world has changed unexpectedly since @StanfordHAI scheduled its follow-up COVID+AI: The Road Ahead event for today 9:15am Pacific. But not only is the backdrop picture oddly apt, the need to rebuild a better more human-centered future is more urgent. https://t.co/LDzBvK3Mr0 https://t.co/4q07TzrJkq
OpenCOVID + AI: The Road Ahead
This agenda may be updated due to speaker availability and scheduling changes. Speakers: John Etchemendy, Denning Family Co-Director, Stanford Institute for Human-Centered …