🤩 Fab, quick guide to parameterized reporting (w/ code and video):
— Mara Averick (@dataandme) October 28, 2020
⚡️ “How to Automate PDF Reporting with R” by @mdancho84 https://t.co/IecRtHpIys via @bizScienc #rstats pic.twitter.com/EoiV53jjym
🤩 Fab, quick guide to parameterized reporting (w/ code and video):
— Mara Averick (@dataandme) October 28, 2020
⚡️ “How to Automate PDF Reporting with R” by @mdancho84 https://t.co/IecRtHpIys via @bizScienc #rstats pic.twitter.com/EoiV53jjym
Presenting algorithms for causal reasoning in Probability Trees. PTs are causal models of generative processes that can represent context-specific causal dependencies, ideal for causal induction, RL and games: https://t.co/Ff8aHMKuY6
— DeepMind (@DeepMind) October 28, 2020
Colab tutorial: https://t.co/J0Y8foKCYi pic.twitter.com/UQ6rDwDQX5
The misuse of colour in science communication https://t.co/r1TOsPHnd9
— Dan Quintana (@dsquintana) October 28, 2020
"We highlight ways for the scientific community to identify and prevent the misuse of colour in science, and call for a proactive step away from colour misuse among the community, publishers, and the press" pic.twitter.com/WNWDoOAsNz
Faster feature engineering end to end on @NVIDIA #GPU, that's @RAPIDSai & @dask_dev. The top solution: good ole' @XGBoostProject & Dask-cuDF. No fancy #DeepLearning needed. Really proud of everyone involved. RAPIDS is even faster on Ampere & each release gets even better 🔥 https://t.co/AMUWXVcO9e
— Joshua Patterson (@datametrician) October 27, 2020
The slides for my talk are available at https://t.co/n0uIw1uX5h https://t.co/gn5giKV10C
— Rob J Hyndman (@robjhyndman) October 26, 2020
Now available to take for free online: MIT's class on Machine Learning in Healthcare.
— MIT CSAIL (@MIT_CSAIL) October 26, 2020
Videos, slides, notes & more: https://t.co/USoIwqpQuM#MondayMotivation #MLforHC #HealthcareAI #aihealthcare pic.twitter.com/mXaeoq73KK
My @GlobAICommunity talk on @spacy_io v3.0 is now live! In it, I'm walking through some of the most exciting new features & the ideas behind them.
— Ines Montani 〰️ (@_inesmontani) October 26, 2020
📺 Video: https://t.co/dRQbyZKlnq
🌙 spaCy v3.0 nightly: https://t.co/cpUa14hZTr
💥 Blog post: https://t.co/OfC6AYlJPU pic.twitter.com/ioYD1hfjvT
This 10 min recording shows machine-learning (ML) folks how to join the age of causal inference (CI) with minimal effort, and teaches CI folks how to estimate their hard-earned estimands using ML techniques https://t.co/KarhIo9H5t
— Judea Pearl (@yudapearl) October 26, 2020
See also https://t.co/XasptX38vh
Lots of great details here about building important deep learning algorithms from scratch. https://t.co/ypJd7Vcwqu pic.twitter.com/kZyTQvUzHQ
— Jeremy Howard (@jeremyphoward) October 26, 2020
saddle point pic.twitter.com/RxWU2omLry
— Chris Albon (@chrisalbon) October 23, 2020
We just published a new video by @ClementDelangue who walks you through fine-tuning of a language model with #huggingtweets by @borisdayma & how to use the model hub, zero-shot classification & open-domain question answering! https://t.co/qPUdW94BZv
— Hugging Face (@huggingface) October 22, 2020
Optimizers like SGD, Adam, and Adagrad are very mysterious things. @distillpub has created #interactive #visualizations which get you that *gut instinct* of how they work!!!
— Andrew Trask (@iamtrask) October 21, 2020
For #100DaysOfMLCode folks, learn by *playing* with these visualizations! 👇https://t.co/KpjPEDqjwd pic.twitter.com/8OIw9jCjAP