loss_W = lambda W: self.loss(x, t)
grads = {}
numerical_gradient(loss_W, self.params['W1'])
の部分ですが、numerical_gradientの第二引数は参照渡しになっているようです。
More than 5 years have passed since last update.
ゼロから作るDeep Learning ―Pythonで学ぶディープラーニングの理論と実装のchapter 4のヒント
Last updated at Posted at 2020-04-01
Register as a new user and use Qiita more conveniently
- You get articles that match your needs
- You can efficiently read back useful information
- You can use dark theme