Skip to content

Commit

Permalink
#16
Browse files Browse the repository at this point in the history
An enpirical evaluation of generic convolutional and recurrent networks for sequence modeling
  • Loading branch information
sanshin5050 authored Jul 23, 2018
1 parent fb87b2d commit b3cb0f1
Showing 1 changed file with 15 additions and 0 deletions.
15 changes: 15 additions & 0 deletions CNN_VS_RNN
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
# [An enpirical evaluation of generic convolutional and recurrent networks for sequence modeling](https://arxiv.org/abs/1803.01271)


sequence modeling
時系列データはrecurrent networksが一般的
けど最近あれやん?CNNええのも出てるやん?

じゃあさ系列データ全般でどっちが応用効くんやろな?
だからわいらが比べたったやで。

そしたら、simpleなCNNでRNNに勝っちゃったよと言う論文

なお、CNNはTCN(temporal convolutional network)を採用している模様。

これ詳しく読んだら、復習できそうなので掘り下げ論文に決定。

0 comments on commit b3cb0f1

Please sign in to comment.