Was there a main reason that led to Gradient Descent being the popular choice of optimization algorithms in the field of Machine Learning?
— hardmaru (@hardmaru) July 16, 2021
Good discussion 👇https://t.co/YojG0kI2qb
Was there a main reason that led to Gradient Descent being the popular choice of optimization algorithms in the field of Machine Learning?
— hardmaru (@hardmaru) July 16, 2021
Good discussion 👇https://t.co/YojG0kI2qb
StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN
— AK (@ak92501) July 16, 2021
pdf: https://t.co/0qmMTydUN5
abs: https://t.co/G5AW58eIqx
a temporal GAN for the unconditional generation of high-quality videos pic.twitter.com/30YnWSSdMj
The Benchmark Lottery
— AK (@ak92501) July 16, 2021
pdf: https://t.co/iZEyaKTitc
abs: https://t.co/atYqI7rXLq
proposes the notion of a benchmark lottery that describes the overall fragility of the ML benchmarking process pic.twitter.com/jx3kaPrT6y
I had a great time talking about https://t.co/GEOZuodrZj, AutoML, Software Engineering for ML with @dpbrinkm and Vishnu Rachakonda on the @mlopscommunity Coffee Sessionshttps://t.co/sbzl8xuuUM
— Jeremy Howard (@jeremyphoward) July 15, 2021
PIX is a library built on top of JAX with the goal of providing image processing functions and tools to JAX in a way that they can be optimised and parallelised through jax.jit, jax.vmap and jax.pmap.
— AK (@ak92501) July 15, 2021
github: https://t.co/AXgepSMkBZ pic.twitter.com/F80hdhty7n
In the US since 1980 more than half of all bachelor’s degrees were earned by women. Over the last 40 years computer science became a less popular option for women. Source: https://t.co/OskNXeFFPs pic.twitter.com/crB1Q0fbCa
— Simon Kuestenmacher (@simongerman600) July 15, 2021
There's a new version of the {{modeldata}} package on CRAN. https://t.co/p3DZGk3Xjn
— Max Kuhn (@topepos) July 15, 2021
There is a great data set (tate_text).
We're also going to remove the two OkCupid data sets in the next version. #rstats pic.twitter.com/sEU9M3srUU
Generally Nuanced Deep Learning Framework (GaNDLF) aims to provide an end-to-end solution for DL-related tasks in medical imaging and provide a robust application framework for deployment in clinical workflows.https://t.co/9WPZQeadt7
— PyTorch (@PyTorch) July 15, 2021
Deduplicating Training Data Makes Language Models Better
— AK (@ak92501) July 15, 2021
pdf: https://t.co/w8J8NZ5v7t
abs: https://t.co/4Woo78QjST
Deduplication allows us to train models that emit memorized text ten times less frequently and require fewer train steps to achieve the same or better accuracy pic.twitter.com/sMMud34rj7
For 20 years I used a wide variety of machine learning and optimization algorithms to tackle predictive modeling challenges.
— Jeremy Howard (@jeremyphoward) July 14, 2021
Nowadays, #deeplearning is part of nearly everything I do. In this @MelbCtrDataSci talk, I explain why I made this my focus.https://t.co/ZORIflwNAu
Glad to share our recent success in applying semi-supervised learning to Google's most fundamental product, Search. Our approach, semi-supervised distillation (SSD), is a simplified version of Noisy Student and an alternative to product distillation.
— Thang Luong (@lmthang) July 14, 2021
Blog: https://t.co/kZUUAkr2x7 pic.twitter.com/B5r5PWNwvO
Today's 💡: @tessy_muiruri is a Risk and Analytics professional from Nairobi, Kenya. She used tweets by Kenyans on political candidates to create an EDA and sentiment analysis model. Timely given Kenya's upcoming elections next year. https://t.co/qrCIs22cF6
— Kaggle (@kaggle) July 14, 2021