We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
No description provided.
The text was updated successfully, but these errors were encountered:
第一个问题:为什么引入非线性激励函数?
如果不用激励函数(其实相当于激励函数是f(x) = x),在这种情况下你每一层输出都是上层输入的线性函数,很容易验证,无论你神经网络有多少层,输出都是输入的线性组合,与没有隐藏层效果相当,这种情况就是最原始的感知机(Perceptron)了。正因为上面的原因,我们决定引入非线性函数作为激励函数,这样深层神经网络就有意义了(不再是输入的线性组合,可以逼近任意函数)。最早的想法是sigmoid函数或者tanh函数,输出有界,很容易充当下一层输入(以及一些人的生物解释balabala) 第二个问题:为什么引入Relu呢?
如果不用激励函数(其实相当于激励函数是f(x) = x),在这种情况下你每一层输出都是上层输入的线性函数,很容易验证,无论你神经网络有多少层,输出都是输入的线性组合,与没有隐藏层效果相当,这种情况就是最原始的感知机(Perceptron)了。正因为上面的原因,我们决定引入非线性函数作为激励函数,这样深层神经网络就有意义了(不再是输入的线性组合,可以逼近任意函数)。最早的想法是sigmoid函数或者tanh函数,输出有界,很容易充当下一层输入(以及一些人的生物解释balabala)
Sorry, something went wrong.
No branches or pull requests
No description provided.
The text was updated successfully, but these errors were encountered: