# Overview

## Notation

• We will use n$n$ to represent the number of distinct data points, or observations.

• Let p$p$ denote the number of variables that are available for use in making predictions.

• We will let xij$x_{ij}$ represent the value of the j$j$th variable for the i$i$th observation, where i=1, 2, , n$i=1,\ 2,\ \dots,\ n$, j=1, 2, , p$j=1,\ 2,\ \dots,\ p$.

• We let X$\textbf{X}$ denote a n×p$n \times p$ matrix whose (i,j)$(i,j)$th element is xij$x_{ij}$.That is,

X=x11x21xn1x12x22xn2x1px2pxnp

• We denote xi$x_i$ as the i$i$th row of X$\textbf{X}$. xi$x_i$ is a vector of length p$p$,, containing the p$p$ variable measurements for the i$i$th observation. That is,

xi=xi1xi2xip

• If we are interested in the columns of X$\textbf{X}$, which we will write as x1, x2, , xp$\textbf{x}_1,\ \textbf{x}_2,\ \dots,\ \textbf{x}_p$. That is,

xj=x1jx2jxnj

• If we use these notations, we can write X$\textbf{X}$ as
X=(x1x2xp)

X=xT1xT2xTn

• The T$^T$ notation denotes the transpose of a matrix or vector. For example,

XT=x11x12x1px21x22x2pxn1xn2vdotsxnp

while
xTi=(xi1xi2xip)

• We use yi$y_i$ to denote the i$i$th observation of the variable on which we wish to predict. Hence, we write the set of all n$n$ observations in vector form as

y=y1y2yn

• We always denote a vector of length n in lower case bold e.g.

a=a1a2an

• If a vector not of length n will be denoted in lower case normal font, e.g. a$a$.

• Matrix will be denoted using bold capitals, such as A$\textbf{A}$.

• Random variables will be denoted using capital normal font, e.g. A$A$, regardless of their dimensions.

• To indicate that an object is a scalar, we will use the notation aR$a \in \mathbb{R}$. To indicate that it is a vector of length k$k$, we will use aRk$a \in \mathbb{R}^k$. We will indicate that an object is a r×s$r \times s$ matrix using ARr×s$\textbf{A} \in \mathbb{R}^{r \times s}$.

• Suppose that ARr×d$\textbf{A} \in \mathbb{R}^{r \times d}$ and BRd×s$\textbf{B} \in \mathbb{R}^{d \times s}$. Then the product of A$\textbf{A}$ and B$\textbf{B}$ is denoted AB$\textbf{AB}$. That is, (AB)ij=dk=1aikbkj$(\textbf{A}\textbf{B})_{ij}=\begin{matrix} \sum_{k=1}^d a_{ik}b_{kj} \end{matrix}$. As an example, consider

A=(1324) and B=(5768)

Then
AB=(1324)(5768)=(1×5+2×73×5+4×71×6+2×83×6+4×8)=(19432250)

• 本文已收录于以下专栏：

举报原因： 您举报文章：ESL Overview 色情 政治 抄袭 广告 招聘 骂人 其他 (最多只允许输入30个字)