ML

定义

约定：

$x_j^{(i)}$：训练数据中的第i列中的第j个特征值 value of feature j in the ith training example

$x^{(i)}$：训练数据中第i列 the input (features) of the ith training example

$m$：训练数据集条数 the number of training examples

$n$：特征数量 the number of features

Week1

Cost Function损失函数

Squared error function/Mean squared function均方误差: 解析失败 (语法错误): {\displaystyle J(θ)=\frac{1}{2m}\sum_{i=1}^m(h_θ(x^{(i)})-y^{(i)})^2}
Cross entropy交叉熵: 解析失败 (语法错误): {\displaystyle J(θ)=-\frac{1}{m}\sum_{i=1}^m[y^{(i)}*logh_θ(x^{(i)})+(1-y^{(i)})*log(1-h_θ(x^{(i)}))]}

Gradient Descent梯度下降

解析失败 (语法错误): {\displaystyle θ_j:=θ_j+α\frac{∂}{∂θ_j}J(θ)}
对于线性回归模型，其损失函数为均方误差，故有：
解析失败 (语法错误): {\displaystyle \frac{∂}{∂θ_j}J(θ)= \frac{∂}{∂θ_j}(\frac{1}{2m}\sum_{i=1}^m(h_θ(x^{(i)})-y^{(i)})^2)}

解析失败 (语法错误): {\displaystyle = \frac{1}{2m}\frac{∂}{∂θ_j}(\sum_{i=1}^m(h_θ(x^{(i)})-y^{(i)})^2)}

解析失败 (语法错误): {\displaystyle = \frac{1}{2m}\sum_{i=1}^m( \frac{∂}{∂θ_j}(h_θ(x^{(i)})-y^{(i)})^2 )}

解析失败 (语法错误): {\displaystyle = \frac{1}{m}\sum_{i=1}^m( (h_θ(x^{(i)})-y^{(i)}) \frac{∂}{∂θ_j}h_θ(x^{(i)}) ) //链式求导法式}

解析失败 (语法错误): {\displaystyle = \frac{1}{m}\sum_{i=1}^m( (h_θ(x^{(i)})-y^{(i)}) \frac{∂}{∂θ_j}x^{(i)}θ ) }

解析失败 (语法错误): {\displaystyle = \frac{1}{m}\sum_{i=1}^m( (h_θ(x^{(i)})-y^{(i)}) \frac{∂}{∂θ_j}\sum_{k=0}^{n}x_k^{(i)}θ_k ) }

对于j>=1:

解析失败 (语法错误): {\displaystyle = \frac{1}{m}\sum_{i=1}^m( (h_θ(x^{(i)})-y^{(i)}) x_j^{(i)} ) }

解析失败 (语法错误): {\displaystyle = \frac{1}{m} (h_θ(x)-y) x_{j} }

Week2

Multivariate Linear Regression

解析失败 (语法错误): {\displaystyle h_θ(x) = θ_0x_0 + θ_1x_1 + θ_2x_2 + ... + θ_nx_n}

解析失败 (语法错误): {\displaystyle = [θ_0x_0^{(1)}, θ_0x_0^{(2)}, ..., θ_0x_0^{(m)}] + [θ_1x_1^{(1)}, θ_1x_1^{(2)}, ..., θ_1x_1^{(m)}] + ... + [θ_nx_n^{(1)}, θ_nx_n^{(2)}, ..., θ_nx_n^{(m)}] }

解析失败 (语法错误): {\displaystyle = [θ_0x_0^{(1)}+θ_1x_1^{(1)}+...+θ_nx_n^{(1)}, \ \ \ θ_0x_0^{(2)}+θ_1x_1^{(2)}+...+θ_nx_n^{(2)}, \ \ \ θ_0x_0^{(m)}+θ_1x_1^{(m)}+...+θ_nx_n^{(m)}] }

解析失败 (语法错误): {\displaystyle = θ^Tx}

其中，
解析失败 (语法错误): {\displaystyle x=\begin{vmatrix} x_0 \\ x_1 \\ x_2 \\ ... \\ x_n \end{vmatrix} = \begin{vmatrix} x_0^{(1)} & x_0^{(2)} & ... & x_0^{(m)} \\ x_1^{(1)} & x_1^{(2)} & ... & x_1^{(m)} \\ x_2^{(1)} & x_2^{(2)} & ... & x_2^{(m)} \\ ... & ... & ... & ...\\ x_n^{(1)} & x_n^{(2)} & ... & x_n^{(m)} \\ \end{vmatrix} , θ=\begin{vmatrix} θ_0 \\ θ_1\\ θ_2\\ ...\\ θ_n \end{vmatrix} }

m为训练数据组数，n为特征个数（通常，为了方便处理，会令解析失败 (语法错误): {\displaystyle x_0^{(i)}=1, i=1,2,...,m）} 。

Feature Scaling & Standard Normalization

解析失败 (语法错误): {\displaystyle x_i := \frac{x_i-μ_i}{s_i} }
其中，解析失败 (语法错误): {\displaystyle μ_i} 是第i个特征数据x_i的均值，而 $s_i$则要视情况而定：

• Feature Scaling:$s_i$为$x_i$中最大值与最小值的差（max-min）；
• Standard Normalization:$s_i$为$x_i$中数据标准差（standard deviation）。

特别注意，通过 Feature scaling训练出模型后，在进行预测时，同样需要对输入特征数据进行归一化。