台湾大学 机器学习(李宏毅) 2020年春
神经网络、反向传播算法(BP)、梯度消失问题、ReLU函数、Max-out网络、Adam学习率衰减、正则化、Dropout
深度网络的有效性理解(集成化、逻辑电路)
本文为本人学习过程中整理的学习笔记,想顺带学英语所以用英文呈现。发现错误还烦请指正。欢迎交流。
未经同意,请勿转载。
DNN
History
Perceptron
A kind of classifier like Logistic regression using sign function and square error instead of Sigmoid function and cross entropy error.
It’s also a linear model (which can not solve non-linearly separable problem).
Fully Connect Neural Network
-
Designing a network structure is defining a function set.
You need to decide the network structure to let a good function in your function set.
Matrix Operation
Multi-class Classifier Output Layer
Use sum of cross entropy error as loss function.
D D D is the dimension of feature. N N N is the scale of training data.
C ( y , y ^ ) = − ∑ i = 1 D y ^ i ln y i L = ∑ n = 1 N = C n C(y, \hat{y}) = -\sum_{i=1}^D \hat{y}_i \ln y_i \\ L = \sum_{n=1}^N = C^n C(y,y^)=−i=1∑Dy^ilnyiL=n=1∑N=Cn
C n C^n Cn means the n t