Compose sklearn objects the way you compose layers in Keras. Neat. https://t.co/iFx5pNXJ2n pic.twitter.com/i9gZx6y2RK
— Reza Zadeh (@Reza_Zadeh) November 17, 2019
Compose sklearn objects the way you compose layers in Keras. Neat. https://t.co/iFx5pNXJ2n pic.twitter.com/i9gZx6y2RK
— Reza Zadeh (@Reza_Zadeh) November 17, 2019
Did you know that Keras Tuner supports sklearn? Awesome!
— Josh Gordon (@random_forests) November 17, 2019
Website: https://t.co/FmQBwvOyyQ
Example: https://t.co/A7z3CYyduL
So happy to see this.
Tensorflow for R: Variational convnets with tfprobability https://t.co/wMHh79mlRX #rstats #rkeras pic.twitter.com/aKTcnqRNfX
— RStudio (@rstudio) November 13, 2019
To all the Bayesian enthusiasts: Please check out our (Jonah Gabry, @mjskay and my) new R package 'posterior' which is designed to help users and developers working with posterior (and prior) draws. The current alpha version is available at https://t.co/2qleIBF5pU
— Paul Bürkner (@paulbuerkner) November 12, 2019
Want to make a beautiful CV in < 20 minutes that works online AND when you print it? Check out pagedown, which has templates for CVs, business cards, posters, and more!#rstatsdc @sctyner https://t.co/HoyRc5MeX2 pic.twitter.com/5CUsk1EXTD
— Emily Robinson (@robinson_es) November 8, 2019
torchvision v0.4.2: Optimized video reader backend
— PyTorch (@PyTorch) November 7, 2019
This minor release provides up to 6x speedup for video reading using a new backend option.
Read more at: https://t.co/p2nKoKUX5g
Just submitted our new automated meta-analysis tool for publication: https://t.co/zzBDwuOb7x
— Gael Varoquaux (@GaelVaroquaux) November 6, 2019
I think that the tool is super useful. I dread that it might not be deemed neurosciency enough by peer review.
In the mean time, use it to do good science! pic.twitter.com/jpMH8Uwy2j
To provide the biomedical community the latest state-of-the-art #NLP models, @NVIDIA has released NVIDIA BioBERT, an optimized version of BioBERT that leverages automatic mixed precision to produce faster training times while maintaining target accuracy. #GTC19
— NVIDIA AI Developer (@NVIDIAAIDev) November 5, 2019
Spleeter is an amazing open-source project from Deezer (the French Spotify) that uses Deep Learning to do source separation on musical tracks. Built with Keras and TensorFlow. It runs out-of-the-box on CPU!
— François Chollet (@fchollet) November 5, 2019
Blog post: https://t.co/TWCciDjPAS
Code: https://t.co/Cx8EpApSqA pic.twitter.com/5Xu8Lldwy9
We're thrilled to bring the power of AutoML to Kaggle! Read more about the integration and why we're excited to put it in the hands of our 3.5M strong community in this blog post by @GoogleCloud: https://t.co/W5MjTxvMIk
— Kaggle (@kaggle) November 4, 2019
📦 Newness in one of my fave EDA pkgs…
— Mara Averick (@dataandme) November 4, 2019
🙌 "(Re)introducing skimr v2 - A year in the life of an open source R project" by @michaelquinn32 & @ElinWaring https://t.co/u6nUxonjiN #rstats pic.twitter.com/W9HygsMG02
At #EMNLP2019 we’re presenting a live demo of VizSeq, a visual analysis toolkit for text generation tasks. Join us at the conference in Hong Kong on Wed at 1:30 - 3:00pm
— Facebook AI (@facebookai) November 4, 2019
Paper: https://t.co/1P4giAh33V
Code: https://t.co/43SX9dRtoP pic.twitter.com/FVIoqnVt3X