文件列表:

base.lua (1965, 2015-05-20)
CONTRIBUTING.md (2659, 2015-05-20)
data\ptb.test.txt (449945, 2015-05-20)
data\ptb.train.txt (5101618, 2015-05-20)
data\ptb.valid.txt (399782, 2015-05-20)
data.lua (1953, 2015-05-20)
LICENSE (10850, 2015-05-20)
main.lua (9102, 2015-05-20)
data (0, 2015-05-20)

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

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：