Part.28_Cost_Function-Neural_Network(ML_Andrew.Ng.)
# Cost Function - Neural Network
2021-10-09
Tags: #MachineLearning #NeuralNetwork #CostFunction
# Basic Concepts
$$\left{\left(x^{(1)}, y^{(1)}\right), \left(x^{(2)}, y^{(2)}\right), \ldots, \left(x^{(m)}, y^{(m)}\right)\right}$$
- $m$: Number of Training Samples - 训练样本数
- $L$: Total Number of Layers in the network - 网络层数
- $s_{l}$ =no. of units (not counting bias unit) in layer - 每一层激活单元数(不包括常数)
# Cost Function: Representation
神经网络用来分类的时候,它的损失函数可以通过对Logistic Regression的损失函数稍加改造来得到:
# 回顾Cost Function of Logistic Regression (With Regularization)
# Intuition of the relation
回顾前面我们提到过的神经网络与Logistic回归的联系:
在Output Layer,