神经网络全连接层+softmax:
如下图:(图片来自StackExchange)
强化说明全连接层:
1.通常将网络最后一个全连接层的输入,即上面的x \mathrm{x}x,视为网络从输入数据提取到的特征。
2.
强化说明softmax:
Yestoday is history, tomorrow is a mystery, but today is a gift.That is why it's called "present". --《Kung Fu Panda》