linkhut

Sort by:

Order:

23 Mar 21

EleutherAI/gpt-neo: An implementation of model parallel GPT2& GPT3-like models, with the ability to scale up to full GPT3 sizes (and possibly more!), using the mesh-tensorflow library.

https://github.com/EleutherAI/gpt-neo/

by chrisSt 4 years ago

Tags:

06 Dec 20

Scaling down Deep Learning

https://greydanus.github.io/2020/12/01/scaling-down/

by chrisSt 5 years ago

Tags:

20 Feb 20

Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data | Uber Engineering Blog

https://eng.uber.com/generative-teaching-networks/

by chrisSt 6 years ago

Tags:

29 Aug 19

Exploring Weight Agnostic Neural Networks | Hacker News

https://news.ycombinator.com/item?id=20817083

by chrisSt 6 years ago

Tags:

Google AI Blog: Exploring Weight Agnostic Neural Networks

https://ai.googleblog.com/2019/08/exploring-weight-agnostic-neural.html

by chrisSt 6 years ago

Tags:

21 May 19

Notes on Weight Initialization for Deep Neural Networks | Hacker News

https://news.ycombinator.com/item?id=19964431

by chrisSt 6 years ago

Tags:

14 May 09

Java Neural Network Framework Neuroph

http://neuroph.sourceforge.net/

by chrisSt 17 years ago

Tags: