Some great articles re algorithmic colonialism:https://t.co/9YmrTNJkaD @Abebab https://t.co/yhNdYXGdxq @amymaxmen https://t.co/BklGSLZRDU @AdrienneLaF https://t.co/AE0OMseKlj @ruchowdh
— Rachel Thomas (@math_rachel) August 19, 2020
Some great articles re algorithmic colonialism:https://t.co/9YmrTNJkaD @Abebab https://t.co/yhNdYXGdxq @amymaxmen https://t.co/BklGSLZRDU @AdrienneLaF https://t.co/AE0OMseKlj @ruchowdh
— Rachel Thomas (@math_rachel) August 19, 2020
Some great articles on bias & fairness:https://t.co/o0hi2pGTsX @random_walker https://t.co/szXolaIsQB @timnitGebru https://t.co/fSH7e6NAH9 @harini824 https://t.co/fVCk5utBVp @samirpassi https://t.co/c4PGpAXEAT @umaivodj
— Rachel Thomas (@math_rachel) August 19, 2020
100x Faster Machine Learning Model Ensembling with @rapidsai cuML and Scikit-Learn Meta-Estimators by Nick Becker https://t.co/GDr3KvsAlS
— Bojan Tunguz (@tunguz) August 18, 2020
Thanks to @djnavarro, the ggplot2 book now has a new chapter on guides (legends and axes): https://t.co/sgUxcP4EOH 🎉 Please let us know if anything is unclear or we've missed something important 😀 #rstats
— Hadley Wickham (@hadleywickham) August 18, 2020
Check out the 3 courses on Tabular Data, NLP and Computer Vision from the awesome Amazon MLU team https://t.co/5RwvtRnyb4 - kudos to Bree, Rachel, Brent and the rest of the crew. Built on https://t.co/fuWTPxe9I1.
— Alex Smola (@smolix) August 18, 2020
A very simple Kaggle notebook that shows how to use KerasTuner to automatically find a high-performing model: https://t.co/LjXfpZJACw
— François Chollet (@fchollet) August 17, 2020
Includes finding the best image augmentation config as part of the parameter search (this is actually one of the most important things to tune) pic.twitter.com/pasgIGHVx5
Someone asked about converting #CSV to @ApacheParquet on the @RAPIDSai slack, and @rodaramburu of @blazingsql reminded us of this excellent blog https://t.co/0w68CrwL8k Even on a @NVIDIAGeForce 1060 we can convert nearly half a TB of data in 30 mins. 🔥🔥🔥 10x cost saving ftw!
— Joshua Patterson (@datametrician) August 17, 2020
Convert horses to zebras with this CycleGAN model by @A_K_Nain, now on https://t.co/m6mT8SrKDD:https://t.co/2KeopZUuJe
— François Chollet (@fchollet) August 17, 2020
Definitely the most concise and elegant implementation of CycleGAN I've seen anywhere -- around 350 lines end-to-end. Train on 8 GPUs by just adding 1 line. pic.twitter.com/ZgHg0TTaHC
This is a great way to learn how to preprocess your own data with 🤗Transformers before using Trainer or a classic PyTorch/Keras training loop! https://t.co/vud0r6nzIO
— Sylvain Gugger (@GuggerSylvain) August 17, 2020
Excited to hear from @cameliacassetet about causal inference for when you can't run an A/B test #rstatsnyc
— David Robinson (@drob) August 15, 2020
You have to be very careful about the assumptions you make and the way you set up the model
But once it's set up, you can do it in #rstats with lm()! pic.twitter.com/9l9dtkpllT
Slides from my #rstatsnyc talk on the widyr package, for widening, operating, and then re-tidying a dataset
— David Robinson (@drob) August 15, 2020
Slides: https://t.co/Zz0b6pa0c3
Package 📦: https://t.co/1gjFrq6qQu pic.twitter.com/PBqXxUzBoY
🤯 Did you know you could reference blocks of code in an .R file from RMD by referencing them by name??@thomas_mock talk (slides at https://t.co/fDBJPbwTGC) is full of great RMarkdown tips - check it out! #rstatsnyc pic.twitter.com/edFo6pdac2
— Emily Robinson (@robinson_es) August 15, 2020