神经网络和深度学习

神经网路基础

2.3 logistic回归损失函数

• Loss (error) function:
  The loss function measures the discrepancy between the prediction (𝑦̂(𝑖)) and the desired output (𝑦(𝑖)).In other words, the loss function computes the error for a single training example.
• Cost function:
  The cost function is the average of the loss function of the entire training set. We are going to find the
  parameters 𝑤 𝑎𝑛𝑑 𝑏 that minimize the overall cost function.

2.4 梯度下降法

• 由上所述, logistic回归是一种有监督的机器学习算法, 总目标就是使Cost function最小. 而Cost function是关于𝑤、𝑏的二元函数, 该学习过程即是不断修正𝑤、𝑏的过程：

while condition_x:
    𝑤 = 𝑤 - α*d_𝑤
    𝑏 = 𝑏 - α*d_𝑏
    pass
# 其中dx是Cost function对x的偏微分

2.5 - 2.6 导数

• 把导数看作函数的斜率(这里有点微积分的基础就会懂，不多记)

2.7 计算图

• 就是tensorflow种compute graph那一套, Andrew这里介绍这个思想主要是想讲前向、后向传播的过程