深度学习英文单词表
转载自：https://blog.csdn.net/u014171091/article/details/101404890
深度学习英文单词表
| 英文/缩写 | 汉语 |
|---|---|
| Absolute value rectification | 绝对值整流 |
| Activation Function | 激活函数 |
| Accumulated error backpropagation | 累积误差反向传播 |
| Acoustic modeling | 声学建模 |
| Acquisition funtion | 采集函数 |
| Actor-critic method | 行为-评判方法 |
| Adaptive bitrate (ABR) algorithm | 自适应比特率算法 |
| Adaptive Resonance Theory/ART | 自适应谐振理论 |
| Addictive model | 加性模型 |
| Adversarial example | 对抗样本 |
| Adversarial Networks | 对抗网络 |
| Affine Layer | 仿射层 |
| Affinity matrix | 亲和矩阵 |
| Agent | 智能体 |
| Algorithm | 算法 |
| Alpha-beta pruning | α-β剪枝 |
| Alternative splicing dataset | 选择性剪接数据集 |
| Analytic gradient | 解析梯度 |
| Ancestral Sampling | 原始采样 |
| Annealed importance sampling | 退火重要采样 |
| Anomaly detection | 异常检测 |
| Application-specific integrated circuit | 专用集成电路 |
| Approximate Bayesian computation | 近似贝叶斯计算 |
| Approximate inference | 近似推断 |
| Approximation | 近似 |
| Architecture | 架构 |
| Area Under ROC Curve/AUC | Roc 曲线下面积 |
| Artificial General Intelligence/AGI | 通用人工智能 |
| Artificial Intelligence/AI | 人工智能 |
| Association analysis | 关联分析 |
| Asymptotically unbiased | 渐近无偏 |
| Asynchoronous Stochastic Gradient Descent | 异步随机梯度下降 |
| Attention mechanism | 注意力机制 |
| Attribute conditional independence assumption | 属性条件独立性假设 |
| Attribute space | 属性空间 |
| Attribute value | 属性值 |
| Augmented Lagrangian | 增广拉格朗日法 |
| Autoencoder | 自编码器 |
| Automatic differentiation | 自动微分 |
| Automatic speech recognition/ASR | 自动语音识别 |
| Automatic summarization | 自动摘要 |
| Auto-regressive network | 自回归网络 |
| Average gradient | 平均梯度 |
| Average-Pooling | 平均池化 |
| Backpropagation/BP | 反向传播 |
| Backpropagation Through Time | 通过时间的反向传播 |
| Backward induction | 逆向归纳 |
| Bag of words/BoW | 词袋 |
| Base learner | 基学习器 |
| Base learning algorithm | 基学习算法 |
| Batch | 批次 |
| Batch Normalization/BN | 批次归一化 |
| Bayes decision rule | 贝叶斯判定准则 |
| Bayes error | 贝叶斯误差 |
| Bayes Model Averaging/BMA | 贝叶斯模型平均 |
| Bayes optimal classifier | 贝叶斯最优分类器 |
| Bayesian decision theory | 贝叶斯决策论 |
| Bayesian network | 贝叶斯网络 |
| Bayesian optimization | 贝叶斯优化 |
| Beam search | 束搜索 |
| Bechmark | 基准 |
| Belief network | 信念网络 |
| Bellman equation | 贝尔曼方程 |
| Between-class scatter matrix | 类间散度矩阵 |
| Bias | 偏置 / 偏差 |
| Biased | 有偏 |
| Biased importance sampling | 有偏重要采样 |
| Bias-variance decomposition | 偏差-方差分解 |
| Bias-Variance Dilemma | 偏差 - 方差困境 |
| Bi-directional Long-Short Term Memory/Bi-LSTM | 双向长短期记忆 |
| Binary classification | 二元分类 |
| Binary relation | 二元关系 |
| Binary sparse coding | 二值稀疏编码 |
| Binomial distribution | 二项分布 |
| Binomial test | 二项检验 |
| Bi-partition | 二分法 |
| Block coordinate descent | 块坐标下降 |
| Block Gibbs Sampling | 块吉布斯采样 |
| Boilerplate code | 样板代码 |
| Boltzmann distribution | 玻尔兹曼分布 |
| Boltzmann machine | 玻尔兹曼机 |
| Bootstrap sampling | 自助采样法／可重复采样／有放回采样 |
| Bootstrapping | 自助法 |
| Bottleneck layer | 瓶颈层 |
| Bounding Boxes | 边界框 |
| Break-Event Point/BEP | 平衡点 |
| Bridge sampling | 桥式采样 |
| Broadcasting | 广播 |
| Burning-in | 磨合 |
| Calculus of variations | 变分法 |
| Calibration | 校准 |
| Canonical | 正则的 |
| Cascade/Coalesced | 级联 |
| Cascade-Correlation | 级联相关 |
| Categorical attribute | 分类属性 |
| Categorical distribution | 范畴分布、分类分布 |
| Causal factor | 因果因子 |
| Causal modeling | 因果模型 |
| Centered difference | 中心差分 |
| Central limit theorem | 中心极限定理 |
| Chain rule | 链式法则 |
| Chordal graph | 弦图 |
| Class-conditional probability | 类条件概率 |
| Classification and regression tree/CART | 分类与回归树 |
| Classifier | 分类器 |
| Class-imbalance | 分类不平衡 |
| Clip gradient | 梯度截断 |
| Clique potential | 团势能 |
| Closed-form | 闭式 |
| Cluster | 簇/类/集群 |
| Cluster analysis | 聚类分析 |
| Clustering | 聚类 |
| Clustering ensemble | 聚类集成 |
| Co-adapting | 共适应 |
| Coding matrix | 编码矩阵 |
| Collaborative filtering | 协同过滤 |
| COLT | 国际学习理论会议 |
| Committee-based learning | 基于委员会的学习 |
| Competitive learning | 竞争型学习 |
| Complete graph | 完全图 |
| Component learner | 组件学习器 |
| Comprehensibility | 可解释性 |
| Computation Cost | 计算成本 |
| Computational Linguistics | 计算语言学 |
| Computer vision | 计算机视觉 |
| Concept drift | 概念漂移 |
| Concept Learning System/CLS | 概念学习系统 |
| Conditional entropy | 条件熵 |
| Conditional mutual information | 条件互信息 |
| Conditional Probability Table/CPT | 条件概率表 |
| Conditional random field/CRF | 条件随机场 |
| Conditional risk | 条件风险 |
| Confidence | 置信度 |
| Confusion matrix | 混淆矩阵 |
| Conjugate directions | 共轭方向 |
| Conjugate distribution | 共轭分布 |
| Conjugate gradient | 共轭梯度 |
| Connection weight | 连接权 |
| Connectionism | 连结主义 |
| Consistency | 一致性／相合性 |
| Consistency convergence | 一致性收敛 |
| Contingency table | 列联表 |
| Continuation method | 延拓法 |
| Continuous attribute | 连续属性 |
| Contractive autoencoder | 收缩自编码器 |
| Contractive neural network | 收缩神经网络 |
| Convex optimization | 凸优化 |
| Convergence | 收敛 |
| Conversational agent | 会话智能体 |
| Convex quadratic programming | 凸二次规划 |
| Convexity | 凸性 |
| Convolutional Boltzmann Machine | 卷积玻尔兹曼机 |
| Convolutional neural network/CNN | 卷积神经网络 |
| Co-occurrence | 同现 |
| Coordinate descent | 坐标下降 |
| Correlation coefficient | 相关系数 |
| Cosine similarity | 余弦相似度 |
| Cost curve | 成本曲线 |
| Cost Function | 成本函数 |
| Cost matrix | 成本矩阵 |
| Cost-sensitive | 成本敏感 |
| Covariance | 协方差 |
| Covariance matrix | 协方差矩阵 |
| Cross entropy | 交叉熵 |
| Cross validation | 交叉验证 |
| Cross-correlation | 互相关函数 |
| Crowdsourcing | 众包 |
| Cumulative function | 累积函数 |
| Curse of dimensionality | 维度灾难 |
| Curve-fitting | 曲线拟合 |
| Cut point | 截断点 |
| Cutting plane algorithm | 割平面法 |
| Data generating distribution | 数据生成分布 |
| Data mining | 数据挖掘 |
| Data parallelism | 数据并行 |
| Data set | 数据集 |
| Data Wrangling | 数据整理 |
| Dataset augmentation | 数据集增强 |
| Debugging strategy | 调试策略 |
| Decision Boundary | 决策边界 |
| Decision stump | 决策树桩 |
| Decision tree | 决策树／判定树 |
| Deconvolutional Network | 解卷积网络 |
| Deduction | 演绎 |
| Deep Belief Network | 深度信念网络 |
| Deep Boltzmann Machine | 深度玻尔兹曼机 |
| Deep circuit | 深度回路 |
| Deep Convolutional Generative Adversarial Network/DCGAN | 深度卷积生成对抗网络 |
| Deep generative model | 深度生成模型 |
| Deep learning | 深度学习 |
| Deep Q-Learning | 深度 Q 学习 |
| Deep Q-Network | 深度 Q 网络 |
| Denoising autoencoder | 去噪自编码器 |
| Denoising score matching | 去噪得分匹配 |
| Density estimation | 密度估计 |
| Density-based clustering | 密度聚类 |
| Detailed balance | 细致平衡 |
| Determinant | 行列式 |
| Deterministic | 确定性 |
| Diagonal matrix | 对角矩阵 |
| Differentiable neural computer | 可微分神经计算机 |
| Differential entropy | 微分熵 |
| Differential equation | 微分方程 |
| Dimensionality reduction algorithm | 降维算法 |
| Directed edge | 有向边 |
| Directed graphical model | 有向图模型 |
| Directional derivative | 方向导数 |
| Dirichlet distribution | 狄利克雷分布 |
| Disagreement measure | 不合度量 |
| Discriminative model | 判别模型 |
| Discriminator | 判别器 |
| Discriminator network | 判别器网络 |
| Distance measure | 距离度量 |
| Distance metric learning | 距离度量学习 |
| Distribution | 分布 |
| Divergence | 散度 |
| Diversity measure | 多样性度量／差异性度量 |
| Domain adaption | 领域自适应 |
| Dominant strategy | 占优策略 |
| Double backprop | 双反向传播 |
| Doubly block circulant matrix | 双重分块循环矩阵 |
| Downsampling | 下采样 |
| D-separation/Directed separation | 有向分离 |
| Dual problem | 对偶问题 |
| Dummy node | 哑结点 |
| Dynamic Fusion | 动态融合 |
| Dynamic programming | 动态规划 |
| Echo state network | 回声状态网络 |
| Edge device | 边缘设备 |
| Eigendecomposition | 特征分解 |
| Eigenvalue | 特征值 |
| Eigenvalue decomposition | 特征值分解 |
| Eigenvector | 特征向量 |
| Element-wise product | 元素对应乘积 |
| Ellipsoid method | 椭球法 |
| Embedding | 嵌套 |
| Emotional analysis | 情绪分析 |
| Empirical conditional entropy | 经验条件熵 |
| Empirical entropy | 经验熵 |
| Empirical error | 经验误差 |
| Empirical risk | 经验风险 |
| End-to-End | 端到端 |
| Energy-based model | 基于能量的模型 |
| Ensemble learning | 集成学习 |
| Ensemble pruning | 集成修剪 |
| Epochs | 轮数/周期 |
| Error Correcting Output Codes/ECOC | 纠错输出码 |
| Error rate | 错误率 |
| Error-ambiguity decomposition | 误差-分歧分解 |
| Euclidean distance | 欧氏距离 |
| Euclidean norm | 欧几里得范数 |
| Evolutionary computation | 演化计算 |
| Exact | 确切的 |
| Expectation-Maximization/EM | 期望最大化 |
| Expected loss | 期望损失 |
| Expert network | 专家网络 |
| Explaining away effect | 相消解释作用 |
| Exploding Gradient Problem | 梯度爆炸问题 |
| Exploitation | 利用 |
| Exploration | 探索 |
| Exponential loss function | 指数损失函数 |
| Extreme Learning Machine/ELM | 超限学习机 |
| Factor analysis | 因子分析 |
| Factorization | 因子分解 |
| Factors of variation | 变差因素 |
| False negative | 假负例 |
| False positive | 假正例 |
| False Positive Rate/FPR | 假正例率 |
| Fault-tolerant asynchronous training | 容错异步训练 |
| Feature engineering | 特征工程 |
| Feature extractor | 特征提取器 |
| Feature map | 特征图 |
| Feature selection | 特征选择 |
| Feature vector | 特征向量 |
| Featured Learning | 特征学习 |
| Feedforward Neural Networks/FNN | 前馈神经网络 |
| Field Programmable Gated Array | 现场可编程门阵列 |
| Fine-tuning | 精调 |
| Finite difference | 有限差分 |
| Fixed point equation | 不动点方程 |
| Flipping output | 翻转法 |
| Fluctuation | 震荡 |
| Folk Theorem | 无名氏定理 |
| Forget gate | 遗忘门 |
| Forward stagewise algorithm | 前向分步算法 |
| Fourier transform | 傅立叶变换 |
| Frequentist | 频率主义学派 |
| Frequentist probability | 频率派概率 |
| Full-rank matrix | 满秩矩阵 |
| Functional derivative | 泛函导数 |
| Functional neuron | 功能神经元 |
| Gain ratio | 增益率 |
| Game payoff | 博弈效用 |
| Game theory | 博弈论 |
| Gated recurrent net/GRN | 门控循环网络 |
| Gaussian kernel function | 高斯核函数 |
| Gaussian Mixture Model | 高斯混合模型 |
| Gaussian Process | 高斯过程 |
| General Problem Solving | 通用问题求解 |
| Generalization | 泛化 |
| Generalization error | 泛化误差 |
| Generalization error bound | 泛化误差上界 |
| Generalized Lagrange function | 广义拉格朗日函数 |
| Generalized linear model | 广义线性模型 |
| Generalized pseudolikelihood | 广义伪似然 |
| Generalized Rayleigh quotient | 广义瑞利商 |
| Generalized score matching | 广义得分匹配 |
| Generative Adversarial Networks/GAN | 生成对抗网络 |
| Generative Model | 生成模型 |
| Generative moment matching network | 生成矩匹配网络 |
| Generator | 生成器 |
| Genetic Algorithm/GA | 遗传算法 |
| Giant magnetoresistance | 巨磁阻 |
| Gibbs sampling | 吉布斯采样 |
| Gini index | 基尼指数 |
| Global contrast normalization | 全局对比度归一化 |
| Global minimum | 全局最小 |
| Global Optimization | 全局优化 |
| Gradient boosting tree | 梯度提升树 |
| Gradient Descent | 梯度下降 |
| Gradient energy distribution | 梯度能量分布 |
| Graph theory | 图论 |
| Grid search | 网格搜索 |
| Ground-truth | 真相／真实 |
| Hard margin | 硬间隔 |
| Hard voting | 硬投票 |
| Harmonic mean | 调和平均 |
| Hesse matrix | 海赛矩阵 |
| Heterogeneous Information Network/HIN | 异质信息网络 |
| Hidden dynamic model | 隐动态模型 |
| Hidden layer | 隐藏层 |
| Hidden Markov Model/HMM | 隐马尔可夫模型 |
| Hierarchical clustering | 层次聚类 |
| Hilbert space | 希尔伯特空间 |
| Hinge loss function | 合页损失函数 |
| Hold-out | 留出法 |
| Homogeneous | 同质 |
| Hybrid computing | 混合计算 |
| Hyperparameter | 超参数 |
| Hypothesis | 假设 |
| Hypothesis test | 假设检验 |
| ICML | 国际机器学习会议 |
| Identity matrix | 单位矩阵 |
| Image restoration | 图像复原 |
| Imperfect Information | 不完美信息 |
| Improved iterative scaling/IIS | 改进的迭代尺度法 |
| Incremental learning | 增量学习 |
| Independent and identically distributed/i.i.d. | 独立同分布 |
| Independent Component Analysis/ICA | 独立成分分析 |
| Independent subspace analysis | 独立子空间分析 |
| 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/ILP | 归纳逻辑程序设计 |
| Inequality constraint | 不等式约束 |
| Inference | 推断 |
| Information entropy | 信息熵 |
| Information gain | 信息增益 |
| Input layer | 输入层 |
| Insensitive loss | 不敏感损失 |
| Instance segmentation | 实例分割 |
| Inter-cluster similarity | 簇间相似度 |
| International Conference for Machine Learning/ICML | 国际机器学习大会 |
| Intra-cluster similarity | 簇内相似度 |
| Intrinsic value | 固有值 |
| Invariance | 不变性 |
| Invert | 求逆 |
| Isometric Mapping/Isomap | 等度量映射 |
| Isotonic regression | 等分回归 |
| Iterative Dichotomiser | 迭代二分器 |
| Jensen-Shannon Divergence/JSD | JS 散度 |
| Kernel method | 核方法 |
| Kernel trick | 核技巧 |
| Kernelized Linear Discriminant Analysis/KLDA | 核线性判别分析 |
| K-fold cross validation | k 折交叉验证／k 倍交叉验证 |
| K-Means Clustering | K - 均值聚类 |
| K-Nearest Neighbours Algorithm/KNN | K近邻算法 |
| Knowledge base | 知识库 |
| Knowledge Engineering | 知识工程 |
| Knowledge graph | 知识图谱 |
| Knowledge Representation | 知识表征 |
| Label space | 标记空间 |
| Lagrange duality | 拉格朗日对偶性 |
| Lagrange multiplier | 拉格朗日乘子 |
| Laplace smoothing | 拉普拉斯平滑 |
| Laplacian correction | 拉普拉斯修正 |
| Latent Dirichlet Allocation/LDA | 隐狄利克雷分布 |
| Latent semantic analysis | 潜在语义分析 |
| Latent variable | 隐变量 |
| Law of large number | 大数定理 |
| Layer-wise Adaptive Rate Scaling/LARS | 层级对应的适应率缩放 |
| Lazy learning | 懒惰学习 |
| Leaky ReLU | 渗漏整流线性单元 |
| Learner | 学习器 |
| Learning by analogy | 类比学习 |
| Learning rate | 学习速率 |
| Learning Vector Quantization/LVQ | 学习向量量化 |
| Least squares regression tree | 最小二乘回归树 |
| Leave-One-Out/LOO | 留一法 |
| Lebesgue-integrable | 勒贝格可积 |
| Left eigenvector | 左特征向量 |
| Leibniz’s rule | 莱布尼兹法则 |
| Linear Discriminant Analysis/LDA | 线性判别 |
| Linear model | 线性模型 |
| Linear Regression | 线性回归 |
| Linear threshold units | 线性阀值单元 |
| Link function | 联系函数 |
| Local conditional probability distribution | 局部条件概率分布 |
| Local contrast normalization | 局部对比度归一化 |
| Local curvature | 局部曲率 |
| Local Invariances | 局部不变性 |
| Local Markov property | 局部马尔可夫性 |
| Local minimum | 局部最小 |
| Log likelihood | 对数似然 |
| Log odds/logit | 对数几率 |
| Logistic Regression | Logistic 回归 |
| Log-likelihood | 对数似然 |
| Log-linear regression | 对数线性回归 |
| Long-Short Term Memory/LSTM | 长短期记忆 |
| Long-term dependency | 长期依赖 |
| 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 translation/MT | 机器翻译 |
| Macron-P | 宏查准率 |
| Macron-R | 宏查全率 |
| Main diagonal | 主对角线 |
| Majority voting | 绝对多数投票法 |
| Manifold assumption | 流形假设 |
| Manifold learning | 流形学习 |
| Manifold tangent classifier | 流形正切分类器 |
| Margin theory | 间隔理论 |
| Marginal distribution | 边缘分布 |
| Marginal independence | 边缘独立性 |
| Marginal probability distribution | 边缘概率分布 |
| Marginalization | 边际化 |
| Markov Chain | 马尔可夫链 |
| Markov Chain Monte Carlo/MCMC | 马尔可夫链蒙特卡罗方法 |
| Markov Random Field | 马尔可夫随机场 |
| Matrix inversion | 逆矩阵 |
| Maximal clique | 最大团 |
| Maximum A Posteriori | 最大后验 |
| Maximum Likelihood Estimation/MLE | 极大似然估计／极大似然法 |
| Maximum margin | 最大间隔 |
| Maximum weighted spanning tree | 最大带权生成树 |
| Max-Pooling | 最大池化 |
| Mean product of Student t-distribution | 学生 t 分布均值乘积 |
| Mean squared error | 均方误差 |
| Mean-covariance restricted Boltzmann machine | 均值-协方差受限玻尔兹曼机 |
| Measure theory | 测度论 |
| Meta-learner | 元学习器 |
| Metric learning | 度量学习 |
| Micro-P | 微查准率 |
| Micro-R | 微查全率 |
| Mini-Batch SGD | 小批次随机梯度下降 |
| Minimal Description Length/MDL | 最小描述长度 |
| Minimax game | 极小极大博弈 |
| Misclassification cost | 误分类成本 |
| Mixture density network | 混合密度网络 |
| Mixture of experts | 混合专家 |
| Model predictive control (MPC) | 模型预测控制 |
| Moment matching | 矩匹配 |
| Momentum | 动量 |
| Monte Carlo Estimate | 蒙特卡洛估计 |
| Moore’s Law | 摩尔定律 |
| Moral graph | 道德图／端正图 |
| Multi-class classification | 多类别分类 |
| Multi-document summarization | 多文档摘要 |
| Multi-kernel learning | 多核学习 |
| Multi-layer feedforward neural networks | 多层前馈神经网络 |
| Multilayer Perceptron/MLP | 多层感知器 |
| Multimodal learning | 多模态学习 |
| Multinomial distribution | 多项分布 |
| Multiple Dimensional Scaling | 多维缩放 |
| Multiple linear regression | 多元线性回归 |
| Multi-response Linear Regression/MLR | 多响应线性回归 |
| Multivariate normal distribution | 多维正态分布 |
| Mutual information | 互信息 |
| Naive bayes | 朴素贝叶斯 |
| Naive Bayes Classifier | 朴素贝叶斯分类器 |
| Named entity recognition | 命名实体识别 |
| Nash equilibrium | 纳什均衡 |
| Nash reversion | 纳什回归 |
| Natural language generation/NLG | 自然语言生成 |
| Natural language processing | 自然语言处理 |
| Nearest-neighbor search | 最近邻搜索 |
| Negative class | 负类 |
| Negative correlation | 负相关法 |
| Negative definite | 负定 |
| Negative Log Likelihood | 负对数似然 |
| Negative semidefinite | 半负定 |
| Neighbourhood Component Analysis/NCA | 近邻成分分析 |
| Neural Machine Translation | 神经机器翻译 |
| Newton method | 牛顿法 |
| Conference on Neural Information Processing Systems/NIPS | 国际神经信息处理系统会议 |
| No Free Lunch Theorem/NFL | 没有免费的午餐定理 |
| Noise-contrastive estimation | 噪音对比估计 |
| Nominal attribute | 列名属性 |
| Non-convex optimization | 非凸优化 |
| Nonlinear model | 非线性模型 |
| Non-linear oscillation | 非线性振荡 |
| 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 |
| Non-Saturating Game | 非饱和博弈 |
| Norm | 范数 |
| Normalization | 归一化 |
| Nuclear norm | 核范数 |
| Numerical attribute | 数值属性 |
| Numerical optimization | 数值优化 |
| Objective function | 目标函数 |
| Oblique decision tree | 斜决策树 |
| Occam’s razor | 奥卡姆剃刀 |
| Odds | 几率 |
| Offline inference | 离线推断 |
| Off-Policy | 离策略 |
| Offset vector | 偏移向量 |
| One shot learning | 一次性学习 |
| One-Dependent Estimator/ODE | 独依赖估计 |
| Online inference | 在线推断 |
| On-Policy | 在策略 |
| Ordinal attribute | 有序属性 |
| Orthogonal matrix | 正交矩阵 |
| Orthonormal | 标准正交 |
| Outlier | 异常值/离群值 [[5]] |
| Out-of-bag estimate | 包外估计 |
| Output layer | 输出层 |
| Output smearing | 输出调制法 |
| Overcomplete | 过完备 |
| Overfitting | 过拟合／过配 |
| Oversampling | 过采样 |
| Paired t-test | 成对 t 检验 |
| Pairwise | 成对型 |
| Pairwise Markov property | 成对马尔可夫性 |
| Parallel tempering | 并行回火 |
| Parameter | 参数 |
| Parameter estimation | 参数估计 |
| Parameter Server | 参数服务器 |
| Parameter tuning | 调参 |
| Parse tree | 解析树 |
| Partial derivative | 偏导数 |
| Particle Swarm Optimization/PSO | 粒子群优化算法 |
| Part-of-speech tagging | 词性标注 |
| Perceptron | 感知机 |
| Performance measure | 性能度量 |
| Permutation invariant | 置换不变性 |
| Perplexity | 困惑度 |
| Pictorial structure | 图形结构 |
| Plug and Play Generative Network | 即插即用生成网络 |
| Plurality voting | 相对多数投票法 |
| Polarity detection | 极性检测 |
| Polynomial Basis Function | 多项式基函数 |
| Polynomial kernel function | 多项式核函数 |
| Pooling | 池化 |
| Positive class | 正类 |
| Positive definite matrix | 正定矩阵 |
| Posterior inference | 后验推断 |
| Posterior probability | 后验概率 |
| Post-hoc test | 后续检验 |
| Post-pruning | 后剪枝 |
| potential function | 势函数 |
| Power method | 幂方法 |
| Precision | 查准率／精确率 [[5]] |
| Prepruning | 预剪枝 |
| Principal component analysis/PCA | 主成分分析 |
| Principle of multiple explanations | 多释原则 |
| Prior knowledge | 先验知识 |
| Probability Graphical Model | 概率图模型 |
| Proximal Gradient Descent/PGD | 近端梯度下降 |
| Pruning | 剪枝 |
| Pseudo-label | 伪标记 |
| Quadratic Programming | 二次规划 |
| Quantized Neural Network/QNN | 量子化神经网络 |
| Quantum computer | 量子计算机 |
| Quantum Computing | 量子计算 |
| Quantum machine learning | 量子机器学习 |
| Quasi Newton method | 拟牛顿法 |
| Quasi-concave | 拟凹 |
| Radial Basis Function/RBF | 径向基函数 |
| Random Forest Algorithm | 随机森林算法 |
| Random walk | 随机漫步 |
| Recall | 召回率／查全率 |
| Receiver Operating Characteristic/ROC | 受试者工作特征 |
| Rectified Linear Unit/ReLU | 线性修正单元 |
| Recurrent Neural Network | 循环神经网络 |
| Recursive neural network | 递归神经网络 |
| Reference model | 参考模型 |
| Regression | 回归 |
| Regularization | 正则化 |
| Regularizer | 正则化项 |
| Reinforcement learning/RL | 强化学习 |
| Relative entropy | 相对熵 |
| Reparametrization | 重参数化 |
| Representation learning | 表征学习 |
| Representer theorem | 表示定理 |
| Reproducing Kernel Hilbert Space/RKHS | 再生核希尔伯特空间 |
| Re-sampling | 重采样法 |
| Rescaling | 再缩放 |
| Reservoir computing | 储层计算 |
| Residual Blocks | 残差块 |
| Residual Mapping | 残差映射 |
| Residual Network | 残差网络 |
| Restricted Boltzmann Machine/RBM | 受限玻尔兹曼机 |
| Restricted Isometry Property/RIP | 限定等距性 |
| Reverse mode accumulation | 反向模式累加 |
| Re-weighting | 重赋权法 |
| Ridge regression | 岭回归 |
| Robustness | 稳健性/鲁棒性 |
| Root node | 根结点 |
| Rule Engine | 规则引擎 |
| Rule learning | 规则学习 |
| Saddle point | 鞍点 |
| Saddle-free Newton method | 无鞍牛顿法 |
| Saliency map | 显著图 |
| Sample space | 样本空间 |
| Sampling | 采样 |
| Score function | 评分函数 |
| Second derivative | 二阶导数 |
| Second-order method | 二阶方法 |
| Self-contrastive estimation | 自对比估计 |
| Self-Driving | 自动驾驶 |
| Self-Organizing Map/SOM | 自组织映射 |
| Semantic hashing | 语义哈希 |
| Semantic segmentation | 语义分割 |
| Semantic similarity | 语义相似度 |
| 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 | 半受限波尔兹曼机 |
| 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 |
| Shannon entropy | 香农熵 |
| Shift invariance | 平移不变性 |
| Siamese Network | 孪生网络 |
| Similarity measure | 相似度度量 |
| Simulated annealing | 模拟退火 |
| Simultaneous localization and mapping/SLAM | 同步定位与地图构建 |
| Singular value | 奇异值 |
| Singular Value Decomposition | 奇异值分解 |
| Slack variables | 松弛变量 |
| Slowness principle | 慢性原则 |
| Smoothing | 平滑 |
| Smoothness prior | 平滑先验 |
| Soft margin | 软间隔 |
| Soft margin maximization | 软间隔最大化 |
| Soft voting | 软投票 |
| Sparse activation | 稀疏激活 |
| Sparse coding | 稀疏编码 |
| Sparse connectivity | 稀疏连接 |
| Sparse initialization | 稀疏初始化 |
| Sparse representation | 稀疏表征 |
| Sparsity | 稀疏性 |
| Specialization | 特化 |
| Spectral Clustering | 谱聚类 |
| Spectral radius | 谱半径 |
| Speech Recognition | 语音识别 |
| Spiking Neural Nets | 脉冲神经网络 |
| Splitting variable | 切分变量 |
| Squashing function | 挤压函数 |
| Stability-plasticity dilemma | 可塑性-稳定性困境 |
| Stacked Deconvolutional Network/SDN | 堆叠解卷积网络 |
| Standard deviation | 标准差 |
| Static game | 静态博弈 |
| Stationary distribution | 稳态分布 |
| Stationary point | 驻点 |
| Statistical learning | 统计学习 |
| Status feature function | 状态特征函数 |
| Stochastic gradient descent | 随机梯度下降 |
| Stochastic Matrix | 随机矩阵 |
| Stochastic maximum likelihood | 随机最大似然 |
| Stochastic Neighbor Embedding | 随机近邻嵌入 |
| Stratified sampling | 分层采样 |
| Structural risk | 结构风险 |
| Structural risk minimization/SRM | 结构风险最小化 |
| Structured variational inference | 结构化变分推断 |
| Subsampling | 下采样 |
| Subspace | 子空间 |
| Supervised learning | 监督学习／有导师学习 |
| support vector expansion | 支持向量展式 |
| Support Vector Machine/SVM | 支持向量机 |
| Surrogat loss | 替代损失 |
| Surrogate function | 替代函数 |
| Symbolic learning | 符号学习 |
| Symbolism | 符号主义 |
| Synset | 同义词集 |
| Synthetic feature | 合成特征 |
| Tangent plane | 切平面 |
| Tangent prop | 正切传播 |
| T-Distribution Stochastic Neighbour Embedding/t-SNE | T分布随机近邻嵌入 |
| Tempered transition | 回火转移 |
| Tensor | 张量 |
| Tensor Processing Units/TPU | 张量处理单元 |
| The least square method | 最小二乘法 |
| Threshold | 阈值 |
| Threshold logic unit | 阈值逻辑单元 |
| Threshold-moving | 阈值移动 |
| Tiled convolution | 平铺卷积 |
| Time delay neural network | 时延神经网络 |
| Time Step | 时间步骤 |
| Tractable | 易处理的 |
| Tokenization | 标记化/分词 |
| Training error | 训练误差 |
| Training instance | 训练实例 |
| Transductive learning | 直推学习 |
| Transfer learning | 迁移学习/转移学习 |
| Treebank | 树库 |
| Trial-by-error | 试错法 |
| Triangulate | 三角形化 |
| Trigram | 三元语法 |
| True negative | 真负例 /[5] |
| True positive | 真正例 /[5] |
| True Positive Rate/TPR | 真正例率 |
| Turing Machine | 图灵机 |
| Twice-learning | 二次学习 |
| Two-dimensional array | 二维数组 |
| Underestimation | 欠估计 |
| Underfitting | 欠拟合／欠配 |
| Undersampling | 欠采样 |
| Understandability | 可理解性 |
| Undirected graphical model | 无向图模型 |
| Unequal cost | 非均等代价 |
| Unit norm | 单位范数 |
| Unit test | 单元测试 |
| Unit variance | 单位方差 |
| Unitary matrix | 酉矩阵 |
| Unit-step function | 单位阶跃函数 |
| Univariate decision tree | 单变量决策树 |
| Unprojection | 反投影 |
| Unshared convolution | 非共享卷积 |
| Unsupervised learning | 无监督学习／无导师学习 |
| Unsupervised layer-wise training | 无监督逐层训练 |
| Upper Confidence Bounds | 上置信界限 |
| Upsampling | 上采样 |
| Vanishing Gradient Problem | 梯度消失问题 |
| Variational derivative | 变分导数 |
| Variational free energy | 变分自由能 |
| Variational inference | 变分推断 |
| VC Theory | VC维理论 |
| Version space | 版本空间 |
| Virtual adversarial example | 虚拟对抗样本 |
| Viterbi algorithm | 维特比算法 |
| Von Neumann architecture | 冯 · 诺伊曼架构 |
| Weak learner | 弱学习器 |
| Weight | 权重 |
| Weight decaying | 权值衰减 |
| Weight sharing | 权共享 |
| Weighted voting | 加权投票法 |
| Wasserstein GAN/WGAN | Wasserstein生成对抗网络 |
| Within-class scatter matrix | 类内散度矩阵 |
| Word embedding | 词嵌入 |
| Word sense disambiguation | 词义消歧 |
| Zero mean | 零均值 |
| Zero-data learning | 零数据学习 |
| Zero-shot learning | 零次学习 |