Matrices are capitalized and vectors are in bold type. We do not generally distinguish between probabilities and probability densities. A subscript asterisk,such as in ,indicates reference to a test set quantity. A superscript asterisk denotes complex conjugate. 矩阵用大写字母表示,向量以粗体显示。我们通常不区分概率与概率密度。下标星号(如 )表示测试集相关量,上标星号代表复共轭。
Symbol Meaning 符号含义
\ left matrix divide: is the vector which solves 左矩阵除法: 是向量 的解,满足
△ an equality which acts as a definition △ 作为定义的等式
equality up to an additive constant 等式相差一个加法常数
\( K
\) determinant of matrix \) 矩阵 的行列式
y Euclidean length of vector ,i.e. y 向量 的欧几里得长度,即
RKHS inner product 的再生核希尔伯特空间内积
RKHS norm 的再生核希尔伯特空间范数
the transpose of vector 向量 的转置
✘ proportional to; e.g. means that is equal to times ✘ 正比于;例如 表示 等于 乘以
a factor which is independent of 与 无关的因子
~ distributed according to; example: ~ 服从...分布;示例:
or partial derivatives (w.r.t. f) 或 关于 f 的偏导数
VV the (Hessian) matrix of second derivatives VV 二阶导数的(海森)矩阵
vector of all 0 ’s (of length ) 全零向量(长度为 )
1 or vector of all 1 ’s (of length ) 1 或 全 1 向量(长度为 )
Cnumber of classes in a classification problem 分类问题中的类别数量
cholesky(A) Cholesky decomposition: is a lower triangular matrix such that cholesky(A) 楚列斯基分解: 是一个下三角矩阵,满足
Gaussian process posterior covariance 高斯过程后验协方差
Ddimension of input space 输入空间维度
Ddata set: 数据集:
diag(w) (vector argument) a diagonal matrix containing the elements of vector diag(w)(向量参数)一个对角矩阵,其元素由向量 组成
(matrix argument) a vector containing the diagonal elements of matrix (矩阵参数)一个向量,包含矩阵 的对角线元素
Kronecker delta, iff and 0 otherwise 克罗内克δ函数,当 时等于 ,否则为 0
or expectation; expectation of when 或 期望;当 时 的期望
or Gaussian process (or vector of) latent function values, 或 高斯过程(或向量)的潜在函数值,
Gaussian process (posterior) prediction (random variable) 高斯过程(后验)预测(随机变量)
Gaussian process posterior mean 高斯过程后验均值
Gaussian process: ,the function is distributed as a 高斯过程: ,函数 服从以
Gaussian process with mean function and covariance function 高斯过程分布,其均值函数为 ,协方差函数为
or either fixed basis function (or set of basis functions) or weight function 或 可以是固定基函数(或一组基函数)或权重函数
or set of basis functions evaluated at all training points 或 表示在所有训练点处评估得到的一组基函数
or the identity matrix (of size ) 或 单位矩阵(大小为 )
Bessel function of the first kind 第一类贝塞尔函数
covariance (or kernel) function evaluated at and 在 和 处评估的协方差(或核)函数
or covariance (or Gram) matrix 或 协方差(或 Gram)矩阵
matrix ,the covariance between training and test cases 矩阵 ,训练集与测试集之间的协方差
or vector,short for ,when there is only a single test case 或 向量, 的简称,当仅存在单一测试用例时
or covariance matrix for the (noise free) values 或 (无噪声) 值的协方差矩阵