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，值得收藏！
| 英文术语 | 中文翻译 |
|---|---|
| 0-1 Loss Function | 0-1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 Boosting | AdaBoost |
| Adaptive Gradient Algorithm | AdaGrad |
| Adaptive Moment Estimation Algorithm | Adam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 Pruning | α-β修剪法 |
| Anomaly Detection | 异常检测 |
| Approximate Inference | 近似推断 |
| Area Under ROC Curve | AUC |
| Artificial 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 |
| BFGS | BFGS |
| Bias | 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 Understudy | BLEU |
| Binary 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 |
| Boosting | Boosting |
| Bootstrap Aggregating | Bagging |
| Bootstrap 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-Powell | DFP |
| Decision 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-Delta | Delta-Bar-Delta |
| Denoising | 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Boosting |
| Dropout 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 Norm | Frobenius 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RNN |
| Gaussian 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 Matrix | Gram 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 Product | Hadamard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 Inequality | Jensen不等式 |
| Joint Probability Distribution | 联合概率分布 |
| K-Armed Bandit Problem | k-摇臂老虎机 |
| K-Fold Cross Validation | k 折交叉验证 |
| Karush-Kuhn-Tucker Condition | KKT条件 |
| Karush–Kuhn–Tucker | Karush–Kuhn–Tucker |
| Kernel 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 Divergence | KL散度 |
| L-BFGS | L-BFGS |
| Label | 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 Model | N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-Learnable | PAC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 Network | Sigmoid信念网络 |
| Sigmoid Function | Sigmoid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 |
| Softmax | Softmax/软最大化 |
| Softmax Function | Softmax函数/软最大化函数 |
| Softmax Regression | Softmax回归/软最大化回归 |
| Softplus Function | Softplus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 Regularization | Tikhonov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 |
| Transformer | Transformer |
| Transformer Model | Transformer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-Structure | V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 Dimension | VC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 |
