LoginSignup
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

@taktakeuchi

DNN_後編1 (演習結果と考察)

Posted at

深層学習3-3,4 Jupyter演習　（Section1：再帰型ニューラルネットワークの概念）Section1-1：RNN全体像

[3_1_simple_RNN]

【演習実施結果】

image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png
image.png

【考察】

・活性化関数にReLUを使った場合、勾配爆発が起ってしまい、学習に失敗した。
・今回初めて活性化関数に、Hyperbolic Tangent関数を適用してみた。Hyperbolic Tangentは、RNNではよく使われる。

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
Sign upLogin
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?