Skip to content

Latest commit

 

History

History
229 lines (115 loc) · 3.21 KB

TERMINOLOGY.md

File metadata and controls

229 lines (115 loc) · 3.21 KB

英汉术语对照

鞍点,saddle point

背景窗口,context window

背景词,context word

背景向量,context vector

变换,transform

编码器,encoder

标签,label

步幅,stride

参数,parameter

超参数,hyper-parameter

层序softmax,hierarchical softmax

成本,cost

词嵌入,word embedding

词向量,word vector

池化层,pooling layer

稠密,dense

大小,size

导入,import

迭代周期(周期),epoch

迭代模型参数,update model parameter(s)

丢弃法,dropout

动量法,momentum (method)

独立同分布,independent and identically distributed (i.i.d.)

端到端,end-to-end

多层感知机,multilayer perceptron

二元分类,binary classification

二次采样,subsample

发散,diverge

泛化,generalization

泛化误差,generalization error

方差,variance

访问参数,access parameters

非凸优化,non-convex optimization

分桶,bucketing

分类,classification

分类器,classifier

分词方式,tokenizer/tokenization

负采样,negative sampling

共现词频,co-occurrence frequency

归一化,normalization

过滤器,filter

过拟合,overfitting

恒等映射,identity mapping

假设,hypothesis

基准,baseline

激活函数,activation function

解码器,decoder

经验风险最小化,empirical risk minimization

局部最小值,local minimum

卷积核,kernel

卷积神经网络,convolutional neural network

决策边界,decision boundary

均值,mean

均方误差,mean squared error

均匀采样,uniform sampling

块,block

困惑度,perplexity

连结,concatenate

类,class

交叉熵,cross-entropy

连续词袋模型,continous bag-of-words (CBOW) model

零张量,zero tensor

流水线,pipeline

softmax回归,softmax regression

模型参数,model parameter

模型复杂度,model complexity

偏差,bias

偏导数,partial derivative

批量,batch

平均池化层,average pooling layer

欠拟合,underfitting

情感分析,sentiment analysis

全连接层,fully connected layer

权重,weight

实例,instance

收敛,converge

属性,property

数值方法,numerical method

数据集,data set

数据样本,data instance

损失函数,loss function

双向循环神经网络,bidirectional recurrent neural network

特征,feature

特征值,eigenvalue

梯度,gradient

梯度裁剪,gradient clipping

填充,padding

跳字模型,skip-gram model

调参,tune hyper-parameter

通道,channel

凸优化,convex optimization

图像,image

未知词符号,unknown token

无偏估计,unbiased estimate

误差,error

小批量,mini-batch

小批量梯度,mini-batch gradient

线性模型,linear model

线性回归,linear regression

协同过滤,collaborative filtering

学习率,learning rate

训练误差,training error

循环神经网络,recurrent neural network

样本,example

一维梯度下降,gradient descent in one-dimensional space

隐藏变量,hidden variable

隐藏层,hidden layer

优化器,optimizer

运算符,operator

真实值,ground truth

指标,metric

支持向量机,support vector machine

注意力机制模型,attention model

准确率,accuracy