Skip to content

fast.ai Blog company blog

AdamW and Super-convergence is now the fastest way to train neural nets

fast.ai

Read on fast.ai → Discuss on HN (37) Archived copy

Points: 329
HN comments: 37
Submissions: 1
Cited by: 0 commenters

AI & Machine Learning Software Engineering 2018

On Hacker News

Submitted	Title on HN	Points	Comments
Jul 3, 2018	AdamW and Super-convergence is now the fastest way to train neural nets by tim_sw	329	37

More from fast.ai Blog

All 28 posts →

I Violated a Code of Conduct

20201,214 points912 commentscited by 10Society, Policy & Culture details

Fast.ai releases new deep learning course, libraries, and book

2020799 points81 comments AI & Machine Learning details

Deep Learning for Coders – Launching Deep Learning Part 2

2017716 points91 comments AI & Machine Learning details

Practical Deep Learning for Coders 2019

2019556 points75 comments AI & Machine Learning details

Computational Linear Algebra

2017537 points55 commentscited by 5AI & Machine Learning details

Can LLMs learn from a single example?

2023440 points139 commentscited by 5AI & Machine Learning details

Related posts from the same era

Google Duplex: An AI System for Accomplishing Real World Tasks Over the Phone

Google AI Blog20181,875 points750 commentscited by 10 details

Microsoft is investing $1B in OpenAI

OpenAI Blog20191,119 points592 commentscited by 3 details

AI winter is well on its way

Filip Piekniewski2018993 points492 commentscited by 3 details

AlphaGo Zero: Learning from scratch

DeepMind Blog2017923 points311 commentscited by 5 details

Lessons learned building an ML trading system

tradientblog.com2019914 points187 comments details

AI Clones Your Voice After Listening for 5 Seconds (2018)

Google on GitHub2019911 points319 commentscited by 5 details