https://github.com/wojzaremba/lstm

https://github.com/wojzaremba/lstm

Last synced: 7 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/wojzaremba/lstm
• Owner: wojzaremba
• License: apache-2.0
• Created: 2015-02-13T17:20:46.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2018-08-21T20:06:21.000Z (about 6 years ago)
• Last Synced: 2024-08-02T16:53:28.271Z (3 months ago)
• Language: Lua
• Homepage:
• Size: 2.16 MB
• Stars: 664
• Watchers: 47
• Forks: 287
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
Long Short Term Memory Units

============================

This is self-contained package to train a language model on word level Penn Tree Bank dataset. 

It achieves 115 perplexity for a small model in 1h, and 81 perplexity for a big model in 

a day. Model ensemble of 38 big models gives 69 perplexity.

This code is derived from https://github.com/wojciechz/learning_to_execute (the same author, but 

a different company).

More information: http://arxiv.org/pdf/1409.2329v4.pdf