You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
--------------原始邮件--------------
发件人:"mick.yi ***@***.***>;
发送时间:2021年4月26日(星期一) 上午10:35
收件人:"yizt/numpy_neural_network" ***@***.***>;
抄送:"Zhipeng Wang ***@***.***>;"Mention ***@***.***>;
主题:Re: [yizt/numpy_neural_network] 多分类损失函数 梯度那里没看懂 (#7)
-----------------------------------
@2hip3nghttps://blog.csdn.net/csuyzt/article/details/81839388 这里有推导
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
https://github.com/yizt/numpy_neural_network/blob/master/nn/losses.py
dy = y_probability - y_true 这个地方的推导不是很理解。大佬这个多分类的损失函数求梯度咋来的啊。
The text was updated successfully, but these errors were encountered: