diff options
author | nicholas-leonard <nick@nikopia.org> | 2016-07-22 22:24:52 +0300 |
---|---|---|
committer | nicholas-leonard <nick@nikopia.org> | 2016-07-22 22:24:52 +0300 |
commit | 7992ccb23ef065bb994ca36ad0eb973c15da273f (patch) | |
tree | eb22a0235af4fc02c6e839c3a640b481d6101f91 | |
parent | d20bca37c2e99dc7fc4f8e906324483ebc050c8b (diff) |
add TLDR to results
-rw-r--r-- | blog/_posts/2016-05-11-nce.md | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/blog/_posts/2016-05-11-nce.md b/blog/_posts/2016-05-11-nce.md index 12c94fc..8a7a3ea 100644 --- a/blog/_posts/2016-05-11-nce.md +++ b/blog/_posts/2016-05-11-nce.md @@ -15,8 +15,8 @@ picture: https://raw.githubusercontent.com/torch/torch.github.io/master/blog/_po * [Building a multi-layer LSTM](#nce.lstm) * [Training and evaluation scripts](#nce.script) * [Results](#nce.result) + * [Future work](#nce.future) * [References](#nce.ref) - * [Future Word](#nce.future) In this Torch blog post, we use noise contrastive estimation (NCE) [[2]](#nce.ref) to train a multi-GPU recurrent neural network language model (RNNLM) @@ -25,6 +25,8 @@ The work presented here is the result of many months of on-and-off work. The enormity of the dataset caused us to contribute some novel open-source Torch modules, criteria and even a multi-GPU tensor. We also provide scripts so that you can train and evaluate your own language models. +If you are only interested in generated samples, perplexity and learning curves, please jump to the [results section](#nce.result). + <a name='nce.char'></a> ## Word versus character language models |