Sources Of Uncertainty https://t.co/eZ2bbpDzwV pic.twitter.com/rQRb5D8DcK
— Chris Albon (@chrisalbon) February 5, 2020
Sources Of Uncertainty https://t.co/eZ2bbpDzwV pic.twitter.com/rQRb5D8DcK
— Chris Albon (@chrisalbon) February 5, 2020
See how Kaggler Chris Deotte uses @rapidsai #cuML to accelerate knn 600x in @kaggle #GPU cloud compute environment and augments data for higher accuracy on MNIST - https://t.co/H9aPHCMCsP
— RAPIDS AI (@rapidsai) February 5, 2020
François (@madlag) is both an independent ML researcher investigating sparse efficient models and... an early angel investor in 🤗
— Thomas Wolf (@Thom_Wolf) February 4, 2020
Happy that he agreed to share some of his knowledge and experience on sparse models in a series of posts!
First one is here https://t.co/LfIL1iPUb4
IEEE Fraud @Kaggle Challenge 1st Place Solution with @rapidsai library:https://t.co/x125dun7kl#ml #ai #ds #machinelearning
— Bojan Tunguz (@tunguz) February 4, 2020
I combined the illustrations of Transformer by Jay Alammar and code annotation by harvardnlp lab in one notebook https://t.co/OMdYv1tfrQ
— /MachineLearning (@slashML) February 4, 2020
AdaBoost https://t.co/eZ2bbpDzwV pic.twitter.com/SnDaIFgpT1
— Chris Albon (@chrisalbon) February 3, 2020
Given that data loading can be a major bottleneck in many DL projects, this sounds like an interesting project to check out: "Accelerating Pytorch with Nvidia DALI" --> "on small models it's ~4X faster than the Pytorch dataloader" https://t.co/W11D2OPCFf
— Sebastian Raschka (@rasbt) February 3, 2020
Matthews Correlation Coefficient https://t.co/eZ2bbpDzwV pic.twitter.com/Uz1cAGDXno
— Chris Albon (@chrisalbon) February 2, 2020
The cool kids may be moving to TabNet and NODE, mind you, although I don't have real-world experience of these yet.https://t.co/fiGASmkELY
— Jeremy Howard (@jeremyphoward) February 2, 2020
Curriculum for Reinforcement Learning
— Sebastian Ruder (@seb_ruder) February 1, 2020
"Learning is probably the best superpower we humans have."@lilianweng explores four types of curricula that have been used to help RL models learn to solve complicated tasks.https://t.co/g2qBCBx4oS pic.twitter.com/UTWHt9l3ng
Through this great story from James Briggs, a computational physicist turned data scientist, I came across his totally amazing deep learning notes, which are some of the best I've seen: https://t.co/Jizh7TVQbS pic.twitter.com/gzvmCrJpXr
— Jeremy Howard (@jeremyphoward) January 31, 2020
A comparison of message queues https://t.co/27OoFrhyG2 (by @archerabi from our tech blog)
— Erik Bernhardsson (@fulhack) January 31, 2020