这725个机器学习术语表，太全了！

您想知道的人工智能干货，第一时间送达

你好，我是zhenguo这是几位机器学习权威专家汇总的725个机器学习术语表，非常全面了，值得收藏！英文术语中文翻译0-1 Loss Function0-1损失函数Accept-Reject Sampling Method接受-拒绝抽样法/接受-拒绝采样法Accumulated Error Backpropagation累积误差反向传播Accuracy精度Acquisition Function采集函数Action动作Activation Function激活函数Active Learning主动学习Adaptive Bitrate Algorithm自适应比特率算法Adaptive BoostingAdaBoostAdaptive Gradient AlgorithmAdaGradAdaptive Moment Estimation AlgorithmAdam算法Adaptive Resonance Theory自适应谐振理论Additive Model加性模型Affinity Matrix亲和矩阵Agent智能体Algorithm算法Alpha-Beta Pruningα-β修剪法Anomaly Detection异常检测Approximate Inference近似推断Area Under ROC CurveAUCArtificial Intelligence人工智能Artificial Neural Network人工神经网络Artificial Neuron人工神经元Attention注意力Attention Mechanism注意力机制Attribute属性Attribute Space属性空间Autoencoder自编码器Automatic Differentiation自动微分Autoregressive Model自回归模型Back Propagation反向传播Back Propagation Algorithm反向传播算法Back Propagation Through Time随时间反向传播Backward Induction反向归纳Backward Search反向搜索Bag of Words词袋Bandit赌博机/老虎机Base Learner基学习器Base Learning Algorithm基学习算法Baseline基准Batch批量Batch Normalization批量规范化Bayes Decision Rule贝叶斯决策准则Bayes Model Averaging贝叶斯模型平均Bayes Optimal Classifier贝叶斯最优分类器Bayes' Theorem贝叶斯定理Bayesian Decision Theory贝叶斯决策理论Bayesian Inference贝叶斯推断Bayesian Learning贝叶斯学习Bayesian Network贝叶斯网/贝叶斯网络Bayesian Optimization贝叶斯优化Beam Search束搜索Benchmark基准Belief Network信念网/信念网络Belief Propagation信念传播Bellman Equation贝尔曼方程Bernoulli Distribution伯努利分布Beta Distribution贝塔分布Between-Class Scatter Matrix类间散度矩阵BFGSBFGSBias偏差/偏置Bias In Affine Function偏置Bias In Statistics偏差Bias Shift偏置偏移Bias-Variance Decomposition偏差 - 方差分解Bias-Variance Dilemma偏差 - 方差困境Bidirectional Recurrent Neural Network双向循环神经网络Bigram二元语法Bilingual Evaluation UnderstudyBLEUBinary Classification二分类Binomial Distribution二项分布Binomial Test二项检验Boltzmann Distribution玻尔兹曼分布Boltzmann Machine玻尔兹曼机BoostingBoostingBootstrap AggregatingBaggingBootstrap Sampling自助采样法Bootstrapping自助法/自举法Break-Event Point平衡点Bucketing分桶Calculus of Variations变分法Cascade-Correlation级联相关Catastrophic Forgetting灾难性遗忘Categorical Distribution类别分布Cell单元Chain Rule链式法则Chebyshev Distance切比雪夫距离Class类别Class-Imbalance类别不平衡Classification分类Classification And Regression Tree分类与回归树Classifier分类器Clique团Cluster簇Cluster Assumption聚类假设Clustering聚类Clustering Ensemble聚类集成Co-Training协同训练Coding Matrix编码矩阵Collaborative Filtering协同过滤Competitive Learning竞争型学习Comprehensibility可解释性Computation Graph计算图Computational Learning Theory计算学习理论Conditional Entropy条件熵Conditional Probability条件概率Conditional Probability Distribution条件概率分布Conditional Random Field条件随机场Conditional Risk条件风险Confidence置信度Confusion Matrix混淆矩阵Conjugate Distribution共轭分布Connection Weight连接权Connectionism连接主义Consistency一致性Constrained Optimization约束优化Context Variable上下文变量Context Vector上下文向量Context Window上下文窗口Context Word上下文词Contextual Bandit上下文赌博机/上下文老虎机Contingency Table列联表Continuous Attribute连续属性Contrastive Divergence对比散度Convergence收敛Convex Optimization凸优化Convex Quadratic Programming凸二次规划Convolution卷积Convolutional Kernel卷积核Convolutional Neural Network卷积神经网络Coordinate Descent坐标下降Corpus语料库Correlation Coefficient相关系数Cosine Similarity余弦相似度Cost代价Cost Curve代价曲线Cost Function代价函数Cost Matrix代价矩阵Cost-Sensitive代价敏感Covariance协方差Covariance Matrix协方差矩阵Critical Point临界点Cross Entropy交叉熵Cross Validation交叉验证Curse of Dimensionality维数灾难Cutting Plane Algorithm割平面法Data Mining数据挖掘Data Set数据集Davidon-Fletcher-PowellDFPDecision Boundary决策边界Decision Function决策函数Decision Stump决策树桩Decision Tree决策树Decoder解码器Decoding解码Deconvolution反卷积Deconvolutional Network反卷积网络Deduction演绎Deep Belief Network深度信念网络Deep Boltzmann Machine深度玻尔兹曼机Deep Convolutional Generative Adversarial Network深度卷积生成对抗网络Deep Learning深度学习Deep Neural Network深度神经网络Deep Q-Network深度Q网络Delta-Bar-DeltaDelta-Bar-DeltaDenoising去噪Denoising Autoencoder去噪自编码器Denoising Score Matching去躁分数匹配Density Estimation密度估计Density-Based Clustering密度聚类Derivative导数Determinant行列式Diagonal Matrix对角矩阵Dictionary Learning字典学习Dimension Reduction降维Directed Edge有向边Directed Graphical Model有向图模型Directed Separation有向分离Dirichlet Distribution狄利克雷分布Discriminative Model判别式模型Discriminator判别器Discriminator Network判别网络Distance Measure距离度量Distance Metric Learning距离度量学习Distributed Representation分布式表示Diverge发散Divergence散度Diversity多样性Diversity Measure多样性度量/差异性度量Domain Adaptation领域自适应Dominant Strategy主特征值Dominant Strategy占优策略Down Sampling下采样Dropout暂退法Dropout Boosting暂退BoostingDropout Method暂退法Dual Problem对偶问题Dummy Node哑结点Dynamic Bayesian Network动态贝叶斯网络Dynamic Programming动态规划Early Stopping早停Eigendecomposition特征分解Eigenvalue特征值Element-Wise Product逐元素积Embedding嵌入Empirical Conditional Entropy经验条件熵Empirical Distribution经验分布Empirical Entropy经验熵Empirical Error经验误差Empirical Risk经验风险Empirical Risk Minimization经验风险最小化Encoder编码器Encoding编码End-To-End端到端Energy Function能量函数Energy-Based Model基于能量的模型Ensemble Learning集成学习Ensemble Pruning集成修剪Entropy熵Episode回合Epoch轮Error误差Error Backpropagation Algorithm误差反向传播算法Error Backpropagation误差反向传播Error Correcting Output Codes纠错输出编码Error Rate错误率Error-Ambiguity Decomposition误差－分歧分解Estimator估计/估计量Euclidean Distance欧氏距离Evidence证据Evidence Lower Bound证据下界Exact Inference精确推断Example样例Expectation期望Expectation Maximization期望最大化Expected Loss期望损失Expert System专家系统Exploding Gradient梯度爆炸Exponential Loss Function指数损失函数Factor因子Factorization因子分解Feature特征Feature Engineering特征工程Feature Map特征图Feature Selection特征选择Feature Vector特征向量Featured Learning特征学习Feedforward前馈Feedforward Neural Network前馈神经网络Few-Shot Learning少试学习Filter滤波器Fine-Tuning微调Fluctuation振荡Forget Gate遗忘门Forward Propagation前向传播/正向传播Forward Stagewise Algorithm前向分步算法Fractionally Strided Convolution微步卷积Frobenius NormFrobenius 范数Full Padding全填充Functional泛函Functional Neuron功能神经元Gated Recurrent Unit门控循环单元Gated RNN门控RNNGaussian Distribution高斯分布Gaussian Kernel高斯核Gaussian Kernel Function高斯核函数Gaussian Mixture Model高斯混合模型Gaussian Process高斯过程Generalization Ability泛化能力Generalization Error泛化误差Generalization Error Bound泛化误差上界Generalize泛化Generalized Lagrange Function广义拉格朗日函数Generalized Linear Model广义线性模型Generalized Rayleigh Quotient广义瑞利商Generative Adversarial Network生成对抗网络Generative Model生成式模型Generator生成器Generator Network生成器网络Genetic Algorithm遗传算法Gibbs Distribution吉布斯分布Gibbs Sampling吉布斯采样/吉布斯抽样Gini Index基尼指数Global Markov Property全局马尔可夫性Global Minimum全局最小Gradient梯度Gradient Clipping梯度截断Gradient Descent梯度下降Gradient Descent Method梯度下降法Gradient Exploding Problem梯度爆炸问题Gram MatrixGram 矩阵Graph Convolutional Network图卷积神经网络/图卷积网络Graph Neural Network图神经网络Graphical Model图模型Grid Search网格搜索Ground Truth真实值Hadamard ProductHadamard积Hamming Distance汉明距离Hard Margin硬间隔Hebbian Rule赫布法则Hidden Layer隐藏层Hidden Markov Model隐马尔可夫模型Hidden Variable隐变量Hierarchical Clustering层次聚类Hilbert Space希尔伯特空间Hinge Loss Function合页损失函数/Hinge损失函数Hold-Out留出法Hyperparameter超参数Hyperparameter Optimization超参数优化Hypothesis假设Hypothesis Space假设空间Hypothesis Test假设检验Identity Matrix单位矩阵Imitation Learning模仿学习Importance Sampling重要性采样Improved Iterative Scaling改进的迭代尺度法Incremental Learning增量学习Independent and Identically Distributed独立同分布Indicator Function指示函数Individual Learner个体学习器Induction归纳Inductive Bias归纳偏好Inductive Learning归纳学习Inductive Logic Programming归纳逻辑程序设计Inference推断Information Entropy信息熵Information Gain信息增益Inner Product内积Instance示例Internal Covariate Shift内部协变量偏移Inverse Matrix逆矩阵Inverse Resolution逆归结Isometric Mapping等度量映射Jacobian Matrix雅可比矩阵Jensen InequalityJensen不等式Joint Probability Distribution联合概率分布K-Armed Bandit Problemk-摇臂老虎机K-Fold Cross Validationk 折交叉验证Karush-Kuhn-Tucker ConditionKKT条件Karush–Kuhn–TuckerKarush–Kuhn–TuckerKernel Function核函数Kernel Method核方法Kernel Trick核技巧Kernelized Linear Discriminant Analysis核线性判别分析KL DivergenceKL散度L-BFGSL-BFGSLabel标签Label Space标记空间Lagrange Duality拉格朗日对偶性Lagrange Multiplier拉格朗日乘子Language Model语言模型Laplace Smoothing拉普拉斯平滑Laplacian Correction拉普拉斯修正Latent Dirichlet Allocation潜在狄利克雷分配Latent Semantic Analysis潜在语义分析Latent Variable潜变量/隐变量Law of Large Numbers大数定律Layer Normalization层规范化Lazy Learning懒惰学习Leaky Relu泄漏修正线性单元/泄漏整流线性单元Learner学习器Learning学习Learning By Analogy类比学习Learning Rate学习率Learning Vector Quantization学习向量量化Least Square Method最小二乘法Least Squares Regression Tree最小二乘回归树Left Singular Vector左奇异向量Likelihood似然Linear Chain Conditional Random Field线性链条件随机场Linear Classification Model线性分类模型Linear Classifier线性分类器Linear Dependence线性相关Linear Discriminant Analysis线性判别分析Linear Model线性模型Linear Regression线性回归Link Function联系函数Local Markov Property局部马尔可夫性Local Minima局部极小Local Minimum局部极小Local Representation局部式表示/局部式表征Log Likelihood对数似然函数Log Linear Model对数线性模型Log-Likelihood对数似然Log-Linear Regression对数线性回归Logistic Function对数几率函数Logistic Regression对数几率回归Logit对数几率Long Short Term Memory长短期记忆Long Short-Term Memory Network长短期记忆网络Loopy Belief Propagation环状信念传播Loss Function损失函数Low Rank Matrix Approximation低秩矩阵近似Machine Learning机器学习Macron-R宏查全率Manhattan Distance曼哈顿距离Manifold流形Manifold Assumption流形假设Manifold Learning流形学习Margin间隔Marginal Distribution边缘分布Marginal Independence边缘独立性Marginalization边缘化Markov Chain马尔可夫链Markov Chain Monte Carlo马尔可夫链蒙特卡罗Markov Decision Process马尔可夫决策过程Markov Network马尔可夫网络Markov Process马尔可夫过程Markov Random Field马尔可夫随机场Mask掩码Matrix矩阵Matrix Inversion逆矩阵Max Pooling最大汇聚Maximal Clique最大团Maximum Entropy Model最大熵模型Maximum Likelihood Estimation极大似然估计Maximum Margin最大间隔Mean Filed平均场Mean Pooling平均汇聚Mean Squared Error均方误差Mean-Field平均场Memory Network记忆网络Message Passing消息传递Metric Learning度量学习Micro-R微查全率Minibatch小批量Minimal Description Length最小描述长度Minimax Game极小极大博弈Minkowski Distance闵可夫斯基距离Mixture of Experts混合专家模型Mixture-of-Gaussian高斯混合Model模型Model Selection模型选择Momentum Method动量法Monte Carlo Method蒙特卡罗方法Moral Graph端正图/道德图Moralization道德化Multi-Class Classification多分类Multi-Head Attention多头注意力Multi-Head Self-Attention多头自注意力Multi-Kernel Learning多核学习Multi-Label Learning多标记学习Multi-Layer Feedforward Neural Networks多层前馈神经网络Multi-Layer Perceptron多层感知机Multinomial Distribution多项分布Multiple Dimensional Scaling多维缩放Multiple Linear Regression多元线性回归Multitask Learning多任务学习Multivariate Normal Distribution多元正态分布Mutual Information互信息N-Gram ModelN元模型Naive Bayes Classifier朴素贝叶斯分类器Naive Bayes朴素贝叶斯Nearest Neighbor Classifier最近邻分类器Negative Log Likelihood负对数似然函数Neighbourhood Component Analysis近邻成分分析Net Input净输入Neural Network神经网络Neural Turing Machine神经图灵机Neuron神经元Newton Method牛顿法No Free Lunch Theorem没有免费午餐定理Noise-Contrastive Estimation噪声对比估计Nominal Attribute列名属性Non-Convex Optimization非凸优化Non-Metric Distance非度量距离Non-Negative Matrix Factorization非负矩阵分解Non-Ordinal Attribute无序属性Norm范数Normal Distribution正态分布Normalization规范化Nuclear Norm核范数Number of Epochs轮数Numerical Attribute数值属性Object Detection目标检测Oblique Decision Tree斜决策树Occam's Razor奥卡姆剃刀Odds几率Off-Policy异策略On-Policy同策略One-Dependent Estimator独依赖估计One-Hot独热Online Learning在线学习Optimizer优化器Ordinal Attribute有序属性Orthogonal正交Orthogonal Matrix正交矩阵Out-Of-Bag Estimate包外估计Outlier异常点Over-Parameterized过度参数化Overfitting过拟合Oversampling过采样Pac-LearnablePAC可学习Padding填充Pairwise Markov Property成对马尔可夫性Parallel Distributed Processing分布式并行处理Parameter参数Parameter Estimation参数估计Parameter Space参数空间Parameter Tuning调参Parametric ReLU参数化修正线性单元/参数化整流线性单元Part-Of-Speech Tagging词性标注Partial Derivative偏导数Partially Observable Markov Decision Processes部分可观测马尔可夫决策过程Partition Function配分函数Perceptron感知机Performance Measure性能度量Perplexity困惑度Pointer Network指针网络Policy策略Policy Gradient策略梯度Policy Iteration策略迭代Polynomial Kernel Function多项式核函数Pooling汇聚Pooling Layer汇聚层Positive Definite Matrix正定矩阵Post-Pruning后剪枝Potential Function势函数Power Method幂法Pre-Training预训练Precision查准率/准确率Prepruning预剪枝Primal Problem主问题Primary Visual Cortex初级视觉皮层Principal Component Analysis主成分分析Prior先验Probabilistic Context-Free Grammar概率上下文无关文法Probabilistic Graphical Model概率图模型Probabilistic Model概率模型Probability Density Function概率密度函数Probability Distribution概率分布Probably Approximately Correct概率近似正确Proposal Distribution提议分布Prototype-Based Clustering原型聚类Proximal Gradient Descent近端梯度下降Pruning剪枝Quadratic Loss Function平方损失函数Quadratic Programming二次规划Quasi Newton Method拟牛顿法Radial Basis Function径向基函数Random Forest随机森林Random Sampling随机采样Random Search随机搜索Random Variable随机变量Random Walk随机游走Recall查全率/召回率Receptive Field感受野Reconstruction Error重构误差Rectified Linear Unit修正线性单元/整流线性单元Recurrent Neural Network循环神经网络Recursive Neural Network递归神经网络Regression回归Regularization正则化Regularizer正则化项Reinforcement Learning强化学习Relative Entropy相对熵Reparameterization再参数化/重参数化Representation表示Representation Learning表示学习Representer Theorem表示定理Reproducing Kernel Hilbert Space再生核希尔伯特空间Rescaling再缩放Reset Gate重置门Residual Connection残差连接Residual Network残差网络Restricted Boltzmann Machine受限玻尔兹曼机Reward奖励Ridge Regression岭回归Right Singular Vector右奇异向量Risk风险Robustness稳健性Root Node根结点Rule Learning规则学习Saddle Point鞍点Sample样本Sample Complexity样本复杂度Sample Space样本空间Scalar标量Selective Ensemble选择性集成Self Information自信息Self-Attention自注意力Self-Organizing Map自组织映射网Self-Training自训练Semi-Definite Programming半正定规划Semi-Naive Bayes Classifiers半朴素贝叶斯分类器Semi-Restricted Boltzmann Machine半受限玻尔兹曼机Semi-Supervised Clustering半监督聚类Semi-Supervised Learning半监督学习Semi-Supervised Support Vector Machine半监督支持向量机Sentiment Analysis情感分析Separating Hyperplane分离超平面Sequential Covering序贯覆盖Sigmoid Belief NetworkSigmoid信念网络Sigmoid FunctionSigmoid函数Signed Distance带符号距离Similarity Measure相似度度量Simulated Annealing模拟退火Simultaneous Localization And Mapping即时定位与地图构建Singular Value奇异值Singular Value Decomposition奇异值分解Skip-Gram Model跳元模型Smoothing平滑Soft Margin软间隔Soft Margin Maximization软间隔最大化SoftmaxSoftmax/软最大化Softmax FunctionSoftmax函数/软最大化函数Softmax RegressionSoftmax回归/软最大化回归Softplus FunctionSoftplus函数Span张成子空间Sparse Coding稀疏编码Sparse Representation稀疏表示Sparsity稀疏性Specialization特化Splitting Variable切分变量Squashing Function挤压函数Standard Normal Distribution标准正态分布State状态State Value Function状态值函数State-Action Value Function状态-动作值函数Stationary Distribution平稳分布Stationary Point驻点Statistical Learning统计学习Steepest Descent最速下降法Stochastic Gradient Descent随机梯度下降Stochastic Matrix随机矩阵Stochastic Process随机过程Stratified Sampling分层采样Stride步幅Structural Risk结构风险Structural Risk Minimization结构风险最小化Subsample子采样Subsampling下采样Subset Search子集搜索Subspace子空间Supervised Learning监督学习Support Vector支持向量Support Vector Expansion支持向量展式Support Vector Machine支持向量机Surrogat Loss替代损失Surrogate Function替代函数Surrogate Loss Function代理损失函数Symbolism符号主义Tangent Propagation正切传播Teacher Forcing强制教学Temporal-Difference Learning时序差分学习Tensor张量Test Error测试误差Test Sample测试样本Test Set测试集Threshold阈值Threshold Logic Unit阈值逻辑单元Threshold-Moving阈值移动Tied Weight捆绑权重Tikhonov RegularizationTikhonov正则化Time Delay Neural Network时延神经网络Time Homogenous Markov Chain时间齐次马尔可夫链Time Step时间步Token词元Token词元Tokenization词元化Tokenizer词元分析器Topic Model话题模型Topic Modeling话题分析Trace迹Training训练Training Error训练误差Training Sample训练样本Training Set训练集Transductive Learning直推学习Transductive Transfer Learning直推迁移学习Transfer Learning迁移学习TransformerTransformerTransformer ModelTransformer模型Transpose转置Transposed Convolution转置卷积Trial And Error试错Trigram三元语法Turing Machine图灵机Underfitting欠拟合Undersampling欠采样Undirected Graphical Model无向图模型Uniform Distribution均匀分布Unigram一元语法Unit单元Universal Approximation Theorem通用近似定理Universal Approximator通用近似器Universal Function Approximator通用函数近似器Unknown Token未知词元Unsupervised Layer-Wise Training无监督逐层训练Unsupervised Learning无监督学习Update Gate更新门Upsampling上采样V-StructureV型结构Validation Set验证集Validity Index有效性指标Value Function Approximation值函数近似Value Iteration值迭代Vanishing Gradient Problem梯度消失问题Vapnik-Chervonenkis DimensionVC维Variable Elimination变量消去Variance方差Variational Autoencoder变分自编码器Variational Inference变分推断Vector向量Vector Space Model向量空间模型Version Space版本空间Viterbi Algorithm维特比算法Vocabulary词表Warp线程束Weak Learner弱学习器Weakly Supervised Learning弱监督学习Weight权重Weight Decay权重衰减Weight Sharing权共享Weighted Voting加权投票Whitening白化Winner-Take-All胜者通吃Within-Class Scatter Matrix类内散度矩阵Word Embedding词嵌入Word Sense Disambiguation词义消歧Word Vector词向量Zero Padding零填充Zero-Shot Learning零试学习Zipf's Law齐普夫定律本文来源：Python与算法社区，版权属于原作者，仅用于学术分享