Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Neural Ordinary Differential Equations #1057

Open
icoxfog417 opened this issue Jan 8, 2019 · 3 comments

Comments

1 participant
@icoxfog417
Copy link
Member

commented Jan 8, 2019

一言でいうと

系列データを扱う伝播プロセスは、隠れ層を「都度」再帰的に更新する形で行われる。この「都度」のステップを限界まで細かくすると微分と考えることができ、隠れ層の更新を連続的な形で定義することができる。連続的になることでBPTTのような段階的な勾配計算が不要になる。

論文リンク

https://arxiv.org/abs/1806.07366

著者/所属機関

Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud

  • University of Toronto, Vector Institute

投稿日付(yyyy/MM/dd)

2018/6/19

概要

新規性・差分

手法

結果

コメント

@icoxfog417

This comment has been minimized.

Copy link
Member Author

commented Jan 8, 2019

@icoxfog417 icoxfog417 added this to 2018 in NIPS Jan 8, 2019

@icoxfog417

This comment has been minimized.

@icoxfog417

This comment has been minimized.

Copy link
Member Author

commented Jan 15, 2019

解説スライド。本論文発表後の発展研究まで紹介されている。

https://www.slideshare.net/DeepLearningJP2016/dlneural-ordinary-differential-equations

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.