Letter A
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Absolute value rectification | 绝对值整流 | [1] |
Activation Function | 激活函数 | [1] / [2] |
Accumulated error backpropagation | 累积误差反向传播 | [1] |
Acoustic modeling | 声学建模 | [1] |
Acquisition funtion | 采集函数 | [1] |
Actor-critic method | 行为-评判方法 | [1] |
Adaptive bitrate (ABR) algorithm | 自适应比特率算法 | [1] |
Adaptive Resonance Theory/ART | 自适应谐振理论 | [1] |
Addictive model | 加性模型 | [1] |
Adversarial example | 对抗样本 | [1] |
Adversarial Networks | 对抗网络 | [1] |
Affine Layer | 仿射层 | [1] |
Affinity matrix | 亲和矩阵 | [1] |
Agent | 智能体 | [1] / [2] / [3] / [4] |
Algorithm | 算法 | [1] / [2] / [3] |
Alpha-beta pruning | α-β剪枝 | [1] |
Alternative splicing dataset | 选择性剪接数据集 | [1] |
Analytic gradient | 解析梯度 | [1] |
Ancestral Sampling | 原始采样 | [1] |
Annealed importance sampling | 退火重要采样 | [1] |
Anomaly detection | 异常检测 | [1] |
Application-specific integrated circuit | 专用集成电路 | [1] |
Approximate Bayesian computation | 近似贝叶斯计算 | [1] |
Approximate inference | 近似推断 | [1] |
Approximation | 近似 | [1] |
Architecture | 架构 | [1] |
Area Under ROC Curve/AUC | Roc 曲线下面积 | [1] |
Artificial General Intelligence/AGI | 通用人工智能 | [1] |
Artificial Intelligence/AI | 人工智能 | [1] / [2] / [3] |
Association analysis | 关联分析 | [1] |
Asymptotically unbiased | 渐近无偏 | [1] |
Asynchoronous Stochastic Gradient Descent | 异步随机梯度下降 | [1] |
Attention mechanism | 注意力机制 | [1] / [2] / [3] |
Attribute conditional independence assumption | 属性条件独立性假设 | [1] |
Attribute space | 属性空间 | [1] |
Attribute value | 属性值 | [1] |
Augmented Lagrangian | 增广拉格朗日法 | [1] |
Autoencoder | 自编码器 | [1] |
Automatic differentiation | 自动微分 | [1] |
Automatic speech recognition/ASR | 自动语音识别 | [1] |
Automatic summarization | 自动摘要 | [1] |
Auto-regressive network | 自回归网络 | [1] |
Average gradient | 平均梯度 | [1] |
Average-Pooling | 平均池化 | [1] |
Letter B
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Backpropagation/BP | 反向传播 | [1] |
Backpropagation Through Time | 通过时间的反向传播 | [1] |
Backward induction | 逆向归纳 | [1] |
Bag of words/BoW | 词袋 | [1] |
Base learner | 基学习器 | [1] |
Base learning algorithm | 基学习算法 | [1] |
Batch | 批次 | [1][5] |
Batch Normalization/BN | 批次归一化 | [1] |
Bayes decision rule | 贝叶斯判定准则 | [1] |
Bayes error | 贝叶斯误差 | [1] |
Bayes Model Averaging/BMA | 贝叶斯模型平均 | [1] |
Bayes optimal classifier | 贝叶斯最优分类器 | [1] |
Bayesian decision theory | 贝叶斯决策论 | [1] |
Bayesian network | 贝叶斯网络 | [1] |
Bayesian optimization | 贝叶斯优化 | [1] |
Beam search | 束搜索 | [1] |
Bechmark | 基准 | [1] |
Belief network | 信念网络 | [1] |
Bellman equation | 贝尔曼方程 | [1] |
Between-class scatter matrix | 类间散度矩阵 | [1] |
Bias | 偏置 / 偏差 | [1] |
Biased | 有偏 | [1] |
Biased importance sampling | 有偏重要采样 | [1] |
Bias-variance decomposition | 偏差-方差分解 | [1] |
Bias-Variance Dilemma | 偏差 - 方差困境 | [1] |
Bi-directional Long-Short Term Memory/Bi-LSTM | 双向长短期记忆 | [1] |
Binary classification | 二元分类 | [1] |
Binary relation | 二元关系 | [1] |
Binary sparse coding | 二值稀疏编码 | [1] |
Binomial distribution | 二项分布 | [1] |
Binomial test | 二项检验 | [1] |
Bi-partition | 二分法 | [1] |
Block coordinate descent | 块坐标下降 | [1] |
Block Gibbs Sampling | 块吉布斯采样 | [1] |
Boilerplate code | 样板代码 | [1] |
Boltzmann distribution | 玻尔兹曼分布 | [1] |
Boltzmann machine | 玻尔兹曼机 | [1] |
Bootstrap sampling | 自助采样法/可重复采样/有放回采样 | [1] |
Bootstrapping | 自助法 | [1] |
Bottleneck layer | 瓶颈层 | [1] |
Bounding Boxes | 边界框 | [1] |
Break-Event Point/BEP | 平衡点 | [1] |
Bridge sampling | 桥式采样 | [1] |
Broadcasting | 广播 | [1] |
Burning-in | 磨合 | [1] |
Letter C
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Calculus of variations | 变分法 | [1] |
Calibration | 校准 | [1] |
Canonical | 正则的 | |
Cascade/Coalesced | 级联 | [1] |
Cascade-Correlation | 级联相关 | [1] |
Categorical attribute | 分类属性 | [1][5] |
Categorical distribution | 范畴分布、分类分布 | [1] |
Causal factor | 因果因子 | [1] |
Causal modeling | 因果模型 | [1] |
Centered difference | 中心差分 | [1] |
Central limit theorem | 中心极限定理 | [1] |
Chain rule | 链式法则 | [1] |
Chordal graph | 弦图 | [1] |
Class-conditional probability | 类条件概率 | [1] |
Classification and regression tree/CART | 分类与回归树 | [1] |
Classifier | 分类器 | [1] |
Class-imbalance | 分类不平衡 | [1] |
Clip gradient | 梯度截断 | [1] |
Clique potential | 团势能 | [1] |
Closed-form | 闭式 | [1] |
Cluster | 簇/类/集群 | [1] |
Cluster analysis | 聚类分析 | [1] |
Clustering | 聚类 | [1] / |
Clustering ensemble | 聚类集成 | [1] |
Co-adapting | 共适应 | [1] |
Coding matrix | 编码矩阵 | [1] |
Collaborative filtering | 协同过滤 | [1] |
COLT | 国际学习理论会议 | [1] |
Committee-based learning | 基于委员会的学习 | [1] |
Competitive learning | 竞争型学习 | [1] |
Complete graph | 完全图 | [1] |
Component learner | 组件学习器 | [1] |
Comprehensibility | 可解释性 | [1] |
Computation Cost | 计算成本 | [1] |
Computational Linguistics | 计算语言学 | [1] |
Computer vision | 计算机视觉 | [1] |
Concept drift | 概念漂移 | [1] |
Concept Learning System/CLS | 概念学习系统 | [1] |
Conditional entropy | 条件熵 | [1] |
Conditional mutual information | 条件互信息 | [1] |
Conditional Probability Table/CPT | 条件概率表 | [1] |
Conditional random field/CRF | 条件随机场 | [1] |
Conditional risk | 条件风险 | [1] |
Confidence | 置信度 | [1] |
Confusion matrix | 混淆矩阵 | [1] |
Conjugate directions | 共轭方向 | [1] |
Conjugate distribution | 共轭分布 | [1] |
Conjugate gradient | 共轭梯度 | [1] |
Connection weight | 连接权 | [1] |
Connectionism | 连结主义 | [1] |
Consistency | 一致性/相合性 | [1] |
Consistency convergence | 一致性收敛 | [1] |
Contingency table | 列联表 | [1] |
Continuation method | 延拓法 | [1] |
Continuous attribute | 连续属性 | [1] |
Contractive autoencoder | 收缩自编码器 | [1] |
Contractive neural network | 收缩神经网络 | [1] |
Convex optimization | 凸优化 | [1] |
Convergence | 收敛 | [1] |
Conversational agent | 会话智能体 | [1] |
Convex quadratic programming | 凸二次规划 | [1] |
Convexity | 凸性 | [1] |
Convolutional Boltzmann Machine | 卷积玻尔兹曼机 | [1] |
Convolutional neural network/CNN | 卷积神经网络 | [1]/[2]/[3] |
Co-occurrence | 同现 | [1] |
Coordinate descent | 坐标下降 | [1] |
Correlation coefficient | 相关系数 | [1] |
Cosine similarity | 余弦相似度 | [1] |
Cost curve | 成本曲线 | [1] |
Cost Function | 成本函数 | [1] |
Cost matrix | 成本矩阵 | [1] |
Cost-sensitive | 成本敏感 | [1] |
Covariance | 协方差 | [1] |
Covariance matrix | 协方差矩阵 | [1] |
Cross entropy | 交叉熵 | [1] |
Cross validation | 交叉验证 | [1] |
Cross-correlation | 互相关函数 | [1] |
Crowdsourcing | 众包 | [1] |
Cumulative function | 累积函数 | [1] |
Curse of dimensionality | 维度灾难 | [1] |
Curve-fitting | 曲线拟合 | [1] |
Cut point | 截断点 | [1] |
Cutting plane algorithm | 割平面法 | [1] |
Letter D
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Data generating distribution | 数据生成分布 | [1] |
Data mining | 数据挖掘 | [1] |
Data parallelism | 数据并行 | [1] |
Data set | 数据集 | [1] |
Data Wrangling | 数据整理 | [1] |
Dataset augmentation | 数据集增强 | [1] |
Debugging strategy | 调试策略 | [1] |
Decision Boundary | 决策边界 | [1] |
Decision stump | 决策树桩 | [1] |
Decision tree | 决策树/判定树 | [1]/[2] |
Deconvolutional Network | 解卷积网络 | [1] |
Deduction | 演绎 | [1] |
Deep Belief Network | 深度信念网络 | [1] |
Deep Boltzmann Machine | 深度玻尔兹曼机 | [1] |
Deep circuit | 深度回路 | [1] |
Deep Convolutional Generative Adversarial Network/DCGAN | 深度卷积生成对抗网络 | [1] |
Deep generative model | 深度生成模型 | [1] |
Deep learning | 深度学习 | [1]/[2]/[3] |
Deep neural network/DNN | 深度神经网络 | [1]/[2]/[3] |
Deep Q-Learning | 深度 Q 学习 | [1]/[2] |
Deep Q-Network | 深度 Q 网络 | [1] |
Denoising autoencoder | 去噪自编码器 | [1] |
Denoising score matching | 去噪得分匹配 | [1] |
Density estimation | 密度估计 | [1] |
Density-based clustering | 密度聚类 | [1] |
Detailed balance | 细致平衡 | [1] |
Determinant | 行列式 | [1] |
Deterministic | 确定性 | |
Diagonal matrix | 对角矩阵 | [1] |
Differentiable neural computer | 可微分神经计算机 | [1] |
Differential entropy | 微分熵 | [1] |
Differential equation | 微分方程 | [1] |
Dimensionality reduction algorithm | 降维算法 | [1] |
Directed edge | 有向边 | [1] |
Directed graphical model | 有向图模型 | [1] |
Directional derivative | 方向导数 | [1] |
Dirichlet distribution | 狄利克雷分布 | [1] |
Disagreement measure | 不合度量 | [1] |
Discriminative model | 判别模型 | [1] |
Discriminator | 判别器 | [1] |
Discriminator network | 判别器网络 | [1] |
Distance measure | 距离度量 | [1] |
Distance metric learning | 距离度量学习 | [1] |
Distribution | 分布 | [1] |
Divergence | 散度 | [1] |
Diversity measure | 多样性度量/差异性度量 | [1] |
Domain adaption | 领域自适应 | [1] |
Dominant strategy | 占优策略 | [1] |
Double backprop | 双反向传播 | [1] |
Doubly block circulant matrix | 双重分块循环矩阵 | [1] |
Downsampling | 下采样 | [1] |
D-separation/Directed separation | 有向分离 | [1] |
Dual problem | 对偶问题 | [1] |
Dummy node | 哑结点 | [1] |
Dynamic Fusion | 动态融合 | [1] |
Dynamic programming | 动态规划 | [1] |
Letter E
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Echo state network | 回声状态网络 | [1] |
Edge device | 边缘设备 | [1] |
Eigendecomposition | 特征分解 | [1] |
Eigenvalue | 特征值 | [1] |
Eigenvalue decomposition | 特征值分解 | [1] |
Eigenvector | 特征向量 | [1] |
Element-wise product | 元素对应乘积 | [1] |
Ellipsoid method | 椭球法 | [1] |
Embedding | 嵌套 | [1][5] |
Emotional analysis | 情绪分析 | [1] |
Empirical conditional entropy | 经验条件熵 | [1] |
Empirical entropy | 经验熵 | [1] |
Empirical error | 经验误差 | [1] |
Empirical risk | 经验风险 | [1] |
End-to-End | 端到端 | [1] |
Energy-based model | 基于能量的模型 | [1] |
Ensemble learning | 集成学习 | [1] |
Ensemble pruning | 集成修剪 | [1] |
Epochs | 轮数/周期 | [1][5] |
Error Correcting Output Codes/ECOC | 纠错输出码 | [1] |
Error rate | 错误率 | [1] |
Error-ambiguity decomposition | 误差-分歧分解 | [1] |
Euclidean distance | 欧氏距离 | [1] |
Euclidean norm | 欧几里得范数 | [1] |
Evolutionary computation | 演化计算 | [1] |
Exact | 确切的 | |
Expectation-Maximization/EM | 期望最大化 | [1] |
Expected loss | 期望损失 | [1] |
Expert network | 专家网络 | [1] |
Explaining away effect | 相消解释作用 | [1] |
Exploding Gradient Problem | 梯度爆炸问题 | [1] |
Exploitation | 利用 | [1] |
Exploration | 探索 | [1] |
Exponential loss function | 指数损失函数 | [1] |
Extreme Learning Machine/ELM | 超限学习机 | [1] |
Letter F
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Factor analysis | 因子分析 | [1] |
Factorization | 因子分解 | [1] |
Factors of variation | 变差因素 | [1] |
False negative | 假负例 | [1] |
False positive | 假正例 | [1] |
False Positive Rate/FPR | 假正例率 | [1] |
Fault-tolerant asynchronous training | 容错异步训练 | [1] |
Feature engineering | 特征工程 | [1] |
Feature extractor | 特征提取器 | [1] |
Feature map | 特征图 | [1] |
Feature selection | 特征选择 | [1] |
Feature vector | 特征向量 | [1] |
Featured Learning | 特征学习 | [1] |
Feedforward Neural Networks/FNN | 前馈神经网络 | [1] |
Field Programmable Gated Array | 现场可编程门阵列 | [1] |
Fine-tuning | 精调 | [1] |
Finite difference | 有限差分 | [1] |
Fixed point equation | 不动点方程 | [1] |
Flipping output | 翻转法 | [1] |
Fluctuation | 震荡 | [1] |
Folk Theorem | 无名氏定理 | [1] |
Forget gate | 遗忘门 | [1] |
Forward stagewise algorithm | 前向分步算法 | [1] |
Fourier transform | 傅立叶变换 | [1] |
Frequentist | 频率主义学派 | [1] |
Frequentist probability | 频率派概率 | [1] |
Full-rank matrix | 满秩矩阵 | [1] |
Functional derivative | 泛函导数 | [1] |
Functional neuron | 功能神经元 | [1] |
Letter G
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Gain ratio | 增益率 | [1] |
Game payoff | 博弈效用 | [1] |
Game theory | 博弈论 | [1] |
Gated recurrent net/GRN | 门控循环网络 | [1] |
Gaussian kernel function | 高斯核函数 | [1] |
Gaussian Mixture Model | 高斯混合模型 | [1] |
Gaussian Process | 高斯过程 | [1] |
General Problem Solving | 通用问题求解 | [1] |
Generalization | 泛化 | [1] |
Generalization error | 泛化误差 | [1] |
Generalization error bound | 泛化误差上界 | [1] |
Generalized Lagrange function | 广义拉格朗日函数 | [1] |
Generalized linear model | 广义线性模型 | [1] |
Generalized pseudolikelihood | 广义伪似然 | [1] |
Generalized Rayleigh quotient | 广义瑞利商 | [1] |
Generalized score matching | 广义得分匹配 | [1] |
Generative Adversarial Networks/GAN | 生成对抗网络 | [1]/[2]/[3] |
Generative Model | 生成模型 | [1]/[2]/[3] |
Generative moment matching network | 生成矩匹配网络 | [1] |
Generator | 生成器 | [1] |
Genetic Algorithm/GA | 遗传算法 | [1]/[2]/[3] |
Giant magnetoresistance | 巨磁阻 | [1] |
Gibbs sampling | 吉布斯采样 | [1] |
Gini index | 基尼指数 | [1] |
Global contrast normalization | 全局对比度归一化 | [1] |
Global minimum | 全局最小 | [1] |
Global Optimization | 全局优化 | [1] |
Gradient boosting tree | 梯度提升树 | [1] |
Gradient Descent | 梯度下降 | [1] |
Gradient energy distribution | 梯度能量分布 | [1] |
Graph theory | 图论 | [1] |
Grid search | 网格搜索 | [1] |
Ground-truth | 真相/真实 | [1] |
Letter H
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Hard margin | 硬间隔 | [1] |
Hard voting | 硬投票 | [1] |
Harmonic mean | 调和平均 | [1] |
Hesse matrix | 海赛矩阵 | [1] |
Heterogeneous Information Network/HIN | 异质信息网络 | [1] |
Hidden dynamic model | 隐动态模型 | [1] |
Hidden layer | 隐藏层 | [1] |
Hidden Markov Model/HMM | 隐马尔可夫模型 | [1] |
Hierarchical clustering | 层次聚类 | [1] |
Hilbert space | 希尔伯特空间 | [1] |
Hinge loss function | 合页损失函数 | [1] |
Hold-out | 留出法 | [1] |
Homogeneous | 同质 | [1] |
Hybrid computing | 混合计算 | [1] |
Hyperparameter | 超参数 | [1]/[2] |
Hypothesis | 假设 | [1] |
Hypothesis test | 假设检验 | [1] |
Letter I
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
ICML | 国际机器学习会议 | [1] |
Identity matrix | 单位矩阵 | [1] |
Image restoration | 图像复原 | [1] |
Imperfect Information | 不完美信息 | [1] |
Improved iterative scaling/IIS | 改进的迭代尺度法 | [1] |
Incremental learning | 增量学习 | [1] |
Independent and identically distributed/i.i.d. | 独立同分布 | [1] |
Independent Component Analysis/ICA | 独立成分分析 | [1] |
Independent subspace analysis | 独立子空间分析 | [1] |
Indicator function | 指示函数 | [1] |
Individual learner | 个体学习器 | [1] |
Induction | 归纳 | [1] |
Inductive bias | 归纳偏好 | [1] |
Inductive learning | 归纳学习 | [1] |
Inductive Logic Programming/ILP | 归纳逻辑程序设计 | [1] |
Inequality constraint | 不等式约束 | [1] |
Inference | 推断 | [1] |
Information entropy | 信息熵 | [1] |
Information gain | 信息增益 | [1] |
Input layer | 输入层 | [1] |
Insensitive loss | 不敏感损失 | [1] |
Instance segmentation | 实例分割 | [1] |
Inter-cluster similarity | 簇间相似度 | [1] |
International Conference for Machine Learning/ICML | 国际机器学习大会 | [1] |
Intra-cluster similarity | 簇内相似度 | [1] |
Intrinsic value | 固有值 | [1] |
Invariance | 不变性 | [1] |
Invert | 求逆 | [1] |
Isometric Mapping/Isomap | 等度量映射 | [1] |
Isotonic regression | 等分回归 | [1] |
Iterative Dichotomiser | 迭代二分器 | [1] |
Letter J
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Jensen-Shannon Divergence/JSD | JS 散度 | [1] |
Letter k
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Kernel method | 核方法 | [1] |
Kernel trick | 核技巧 | [1] |
Kernelized Linear Discriminant Analysis/KLDA | 核线性判别分析 | [1] |
K-fold cross validation | k 折交叉验证/k 倍交叉验证 | [1] |
K-Means Clustering | K - 均值聚类 | [1] |
K-Nearest Neighbours Algorithm/KNN | K近邻算法 | [1] |
Knowledge base | 知识库 | [1] |
Knowledge Engineering | 知识工程 | [1] |
Knowledge graph | 知识图谱 | [1]/[2]/[3] |
Knowledge Representation | 知识表征 | [1] |
Letter L
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Label space | 标记空间 | [1] |
Lagrange duality | 拉格朗日对偶性 | [1] |
Lagrange multiplier | 拉格朗日乘子 | [1] |
Laplace smoothing | 拉普拉斯平滑 | [1] |
Laplacian correction | 拉普拉斯修正 | [1] |
Latent Dirichlet Allocation/LDA | 隐狄利克雷分布 | [1] |
Latent semantic analysis | 潜在语义分析 | [1] |
Latent variable | 隐变量 | [1] |
Law of large number | 大数定理 | [1] |
Layer-wise Adaptive Rate Scaling/LARS | 层级对应的适应率缩放 | [1] |
Lazy learning | 懒惰学习 | [1] |
Leaky ReLU | 渗漏整流线性单元 | [1] |
Learner | 学习器 | [1] |
Learning by analogy | 类比学习 | [1] |
Learning rate | 学习速率 | [1] |
Learning Vector Quantization/LVQ | 学习向量量化 | [1] |
Least squares regression tree | 最小二乘回归树 | [1] |
Leave-One-Out/LOO | 留一法 | [1] |
Lebesgue-integrable | 勒贝格可积 | [1] |
Left eigenvector | 左特征向量 | [1] |
Leibniz’s rule | 莱布尼兹法则 | [1] |
Linear Discriminant Analysis/LDA | 线性判别 | [1] |
Linear model | 线性模型 | [1] |
Linear Regression | 线性回归 | [1]/[2] |
Linear threshold units | 线性阀值单元 | [1] |
Link function | 联系函数 | [1] |
Local conditional probability distribution | 局部条件概率分布 | [1] |
Local contrast normalization | 局部对比度归一化 | [1] |
Local curvature | 局部曲率 | [1] |
Local Invariances | 局部不变性 | [1] |
Local Markov property | 局部马尔可夫性 | [1] |
Local minimum | 局部最小 | [1] |
Log likelihood | 对数似然 | [1] |
Log odds/logit | 对数几率 | [1] |
Logistic Regression | Logistic 回归 | [1] |
Log-likelihood | 对数似然 | [1] |
Log-linear regression | 对数线性回归 | [1] |
Long-Short Term Memory/LSTM | 长短期记忆 | [1]/[2]/[3] |
Long-term dependency | 长期依赖 | [1] |
Loopy belief propagation | 环状信念传播 | [1] |
Loss function | 损失函数 | [1] |
Low rank matrix approximation | 低秩矩阵近似 | [1] |
Letter M
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Machine translation/MT | 机器翻译 | [1] |
Macron-P | 宏查准率 | [1] |
Macron-R | 宏查全率 | [1] |
Main diagonal | 主对角线 | [1] |
Majority voting | 绝对多数投票法 | [1] |
Manifold assumption | 流形假设 | [1] |
Manifold learning | 流形学习 | [1] |
Manifold tangent classifier | 流形正切分类器 | [1] |
Margin theory | 间隔理论 | [1] |
Marginal distribution | 边缘分布 | [1] |
Marginal independence | 边缘独立性 | [1] |
Marginal probability distribution | 边缘概率分布 | [1] |
Marginalization | 边际化 | [1] |
Markov Chain | 马尔可夫链 | [1] |
Markov Chain Monte Carlo/MCMC | 马尔可夫链蒙特卡罗方法 | [1] |
Markov Random Field | 马尔可夫随机场 | [1] |
Matrix inversion | 逆矩阵 | [1] |
Maximal clique | 最大团 | [1] |
Maximum A Posteriori | 最大后验 | [1] |
Maximum Likelihood Estimation/MLE | 极大似然估计/极大似然法 | [1] |
Maximum margin | 最大间隔 | [1] |
Maximum weighted spanning tree | 最大带权生成树 | [1] |
Max-Pooling | 最大池化 | [1] |
Mean product of Student t-distribution | 学生 t 分布均值乘积 | [1] |
Mean squared error | 均方误差 | [1] |
Mean-covariance restricted Boltzmann machine | 均值-协方差受限玻尔兹曼机 | [1] |
Measure theory | 测度论 | [1] |
Meta-learner | 元学习器 | [1] |
Metric learning | 度量学习 | [1] |
Micro-P | 微查准率 | [1] |
Micro-R | 微查全率 | [1] |
Mini-Batch SGD | 小批次随机梯度下降 | [1] |
Minimal Description Length/MDL | 最小描述长度 | [1] |
Minimax game | 极小极大博弈 | [1] |
Misclassification cost | 误分类成本 | [1] |
Mixture density network | 混合密度网络 | [1] |
Mixture of experts | 混合专家 | [1] |
Model predictive control (MPC) | 模型预测控制 | [1] |
Moment matching | 矩匹配 | [1] |
Momentum | 动量 | [1] |
Monte Carlo Estimate | 蒙特卡洛估计 | [1] |
Moore's Law | 摩尔定律 | [1] |
Moral graph | 道德图/端正图 | [1] |
Multi-class classification | 多类别分类 | [1] |
Multi-document summarization | 多文档摘要 | [1] |
Multi-kernel learning | 多核学习 | [1] |
Multi-layer feedforward neural networks | 多层前馈神经网络 | [1] |
Multilayer Perceptron/MLP | 多层感知器 | [1] |
Multimodal learning | 多模态学习 | [1] |
Multinomial distribution | 多项分布 | [1] |
Multiple Dimensional Scaling | 多维缩放 | [1] |
Multiple linear regression | 多元线性回归 | [1] |
Multi-response Linear Regression/MLR | 多响应线性回归 | [1] |
Multivariate normal distribution | 多维正态分布 | [1] |
Mutual information | 互信息 | [1] |
Letter N
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Naive bayes | 朴素贝叶斯 | [1] |
Naive Bayes Classifier | 朴素贝叶斯分类器 | [1] |
Named entity recognition | 命名实体识别 | [1] |
Nash equilibrium | 纳什均衡 | [1] |
Nash reversion | 纳什回归 | [1] |
Natural language generation/NLG | 自然语言生成 | [1] |
Natural language processing | 自然语言处理 | [1]/[2]/[3] |
Nearest-neighbor search | 最近邻搜索 | [1] |
Negative class | 负类 | [1] |
Negative correlation | 负相关法 | [1] |
Negative definite | 负定 | [1] |
Negative Log Likelihood | 负对数似然 | [1] |
Negative semidefinite | 半负定 | [1] |
Neighbourhood Component Analysis/NCA | 近邻成分分析 | [1] |
Neural Machine Translation | 神经机器翻译 | [1] |
Neural Turing Machine | 神经图灵机 | [1] |
Neuromorphic Computing | 神经形态计算 | [1]/[2]/[3] |
Newton method | 牛顿法 | [1] |
Conference on Neural Information Processing Systems/NIPS | 国际神经信息处理系统会议 | [1] |
No Free Lunch Theorem/NFL | 没有免费的午餐定理 | [1] |
Noise-contrastive estimation | 噪音对比估计 | [1] |
Nominal attribute | 列名属性 | [1] |
Non-convex optimization | 非凸优化 | [1] |
Nonlinear model | 非线性模型 | [1] |
Non-linear oscillation | 非线性振荡 | [1] |
Non-metric distance | 非度量距离 | [1] |
Non-negative matrix factorization | 非负矩阵分解 | [1] |
Non-ordinal attribute | 无序属性 | [1] |
Non-Saturating Game | 非饱和博弈 | [1] |
Norm | 范数 | [1] |
Normalization | 归一化 | [1] |
Nuclear norm | 核范数 | [1] |
Numerical attribute | 数值属性 | [1] |
Numerical optimization | 数值优化 | [1] |
Letter O
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Objective function | 目标函数 | [1] |
Oblique decision tree | 斜决策树 | [1] |
Occam's razor | 奥卡姆剃刀 | [1] |
Odds | 几率 | [1] |
Offline inference | 离线推断 | [1] |
Off-Policy | 离策略 | [1] |
Offset vector | 偏移向量 | [1] |
One shot learning | 一次性学习 | [1] |
One-Dependent Estimator/ODE | 独依赖估计 | [1] |
Online inference | 在线推断 | [1] |
On-Policy | 在策略 | [1] |
Ordinal attribute | 有序属性 | [1] |
Orthogonal matrix | 正交矩阵 | [1] |
Orthonormal | 标准正交 | [1] |
Outlier | 异常值/离群值 | [1][5] |
Out-of-bag estimate | 包外估计 | [1] |
Output layer | 输出层 | [1] |
Output smearing | 输出调制法 | [1] |
Overcomplete | 过完备 | [1] |
Overfitting | 过拟合/过配 | [1] |
Oversampling | 过采样 | [1] |
Letter P
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Paired t-test | 成对 t 检验 | [1] |
Pairwise | 成对型 | [1] |
Pairwise Markov property | 成对马尔可夫性 | [1] |
Parallel tempering | 并行回火 | [1] |
Parameter | 参数 | [1] |
Parameter estimation | 参数估计 | [1] |
Parameter Server | 参数服务器 | [1] |
Parameter tuning | 调参 | [1] |
Parse tree | 解析树 | [1] |
Partial derivative | 偏导数 | [1] |
Particle Swarm Optimization/PSO | 粒子群优化算法 | [1] |
Part-of-speech tagging | 词性标注 | [1] |
Perceptron | 感知机 | [1] |
Performance measure | 性能度量 | [1] |
Permutation invariant | 置换不变性 | [1] |
Perplexity | 困惑度 | [1] |
Pictorial structure | 图形结构 | [1] |
Plug and Play Generative Network | 即插即用生成网络 | [1] |
Plurality voting | 相对多数投票法 | [1] |
Polarity detection | 极性检测 | [1] |
Polynomial Basis Function | 多项式基函数 | [1] |
Polynomial kernel function | 多项式核函数 | [1] |
Pooling | 池化 | [1] |
Positive class | 正类 | [1] |
Positive definite matrix | 正定矩阵 | [1] |
Posterior inference | 后验推断 | [1] |
Posterior probability | 后验概率 | [1] |
Post-hoc test | 后续检验 | [1] |
Post-pruning | 后剪枝 | [1] |
potential function | 势函数 | [1] |
Power method | 幂方法 | [1] |
Precision | 查准率/精确率 | [1][5] |
Prepruning | 预剪枝 | [1] |
Principal component analysis/PCA | 主成分分析 | [1] |
Principle of multiple explanations | 多释原则 | [1] |
Prior knowledge | 先验知识 | [1] |
Probability Graphical Model | 概率图模型 | [1] |
Proximal Gradient Descent/PGD | 近端梯度下降 | [1] |
Pruning | 剪枝 | [1] |
Pseudo-label | 伪标记 | [1] |
Letter Q
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Quadratic Programming | 二次规划 | [1] |
Quantized Neural Network/QNN | 量子化神经网络 | [1] |
Quantum computer | 量子计算机 | [1]/[2]/[3] |
Quantum Computing | 量子计算 | [1]/[2]/[3] |
Quantum machine learning | 量子机器学习 | [1] |
Quasi Newton method | 拟牛顿法 | [1] |
Quasi-concave | 拟凹 | [1] |
Letter R
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Radial Basis Function/RBF | 径向基函数 | [1] |
Random Forest Algorithm | 随机森林算法 | [1] |
Random walk | 随机漫步 | [1] |
Recall | 召回率/查全率 | [1] |
Receiver Operating Characteristic/ROC | 受试者工作特征 | [1] |
Rectified Linear Unit/ReLU | 线性修正单元 | [1] |
Recurrent Neural Network | 循环神经网络 | [1]/[2]/[3] |
Recursive neural network | 递归神经网络 | [1] |
Reference model | 参考模型 | [1] |
Regression | 回归 | [1] |
Regularization | 正则化 | [1] |
Regularizer | 正则化项 | [1] |
Reinforcement learning/RL | 强化学习 | [1]/[2]/[3] |
Relative entropy | 相对熵 | [1] |
Reparametrization | 重参数化 | [1] |
Representation learning | 表征学习 | [1] |
Representer theorem | 表示定理 | [1] |
Reproducing Kernel Hilbert Space/RKHS | 再生核希尔伯特空间 | [1] |
Re-sampling | 重采样法 | [1] |
Rescaling | 再缩放 | [1] |
Reservoir computing | 储层计算 | [1] |
Residual Blocks | 残差块 | [1] |
Residual Mapping | 残差映射 | [1] |
Residual Network | 残差网络 | [1] |
Restricted Boltzmann Machine/RBM | 受限玻尔兹曼机 | [1] |
Restricted Isometry Property/RIP | 限定等距性 | [1] |
Reverse mode accumulation | 反向模式累加 | [1] |
Re-weighting | 重赋权法 | [1] |
Ridge regression | 岭回归 | [1] |
Robustness | 稳健性/鲁棒性 | [1] |
Root node | 根结点 | [1] |
Rule Engine | 规则引擎 | [1] |
Rule learning | 规则学习 | [1] |
Letter S
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Saddle point | 鞍点 | [1] |
Saddle-free Newton method | 无鞍牛顿法 | [1] |
Saliency map | 显著图 | [1] |
Sample space | 样本空间 | [1] |
Sampling | 采样 | [1] |
Score function | 评分函数 | [1] |
Second derivative | 二阶导数 | [1] |
Second-order method | 二阶方法 | [1] |
Self-contrastive estimation | 自对比估计 | [1] |
Self-Driving | 自动驾驶 | [1]/[2]/[3] |
Self-Organizing Map/SOM | 自组织映射 | [1] |
Semantic hashing | 语义哈希 | [1] |
Semantic segmentation | 语义分割 | [1] |
Semantic similarity | 语义相似度 | [1] |
Semi-Definite Programming | 半正定规划 | [1] |
Semi-naive Bayes classifiers | 半朴素贝叶斯分类器 | [1] |
Semi-restricted Boltzmann Machine | 半受限波尔兹曼机 | [1] |
Semi-Supervised Learning | 半监督学习 | [1]/[2]/[3] |
semi-Supervised Support Vector Machine | 半监督支持向量机 | [1] |
Sentiment analysis | 情感分析 | [1] |
Separating hyperplane | 分离超平面 | [1] |
Shannon entropy | 香农熵 | [1] |
Shift invariance | 平移不变性 | [1] |
Siamese Network | 孪生网络 | [1] |
Sigmoid function | Sigmoid 函数/S 型函数 | [1]/[5] |
Similarity measure | 相似度度量 | [1] |
Simulated annealing | 模拟退火 | [1] |
Simultaneous localization and mapping/SLAM | 同步定位与地图构建 | [1] |
Singular value | 奇异值 | [1] |
Singular Value Decomposition | 奇异值分解 | [1] |
Slack variables | 松弛变量 | [1] |
Slowness principle | 慢性原则 | [1] |
Smoothing | 平滑 | [1] |
Smoothness prior | 平滑先验 | [1] |
Soft margin | 软间隔 | [1] |
Soft margin maximization | 软间隔最大化 | [1] |
Soft voting | 软投票 | [1] |
Sparse activation | 稀疏激活 | [1] |
Sparse coding | 稀疏编码 | [1] |
Sparse connectivity | 稀疏连接 | [1] |
Sparse initialization | 稀疏初始化 | [1] |
Sparse representation | 稀疏表征 | [1] |
Sparsity | 稀疏性 | [1] |
Specialization | 特化 | [1] |
Spectral Clustering | 谱聚类 | [1] |
Spectral radius | 谱半径 | [1] |
Speech Recognition | 语音识别 | [1]/[2]/[3] |
Spiking Neural Nets | 脉冲神经网络 | [1] |
Splitting variable | 切分变量 | [1] |
Squashing function | 挤压函数 | [1] |
Stability-plasticity dilemma | 可塑性-稳定性困境 | [1] |
Stacked Deconvolutional Network/SDN | 堆叠解卷积网络 | [1] |
Standard deviation | 标准差 | [1] |
Static game | 静态博弈 | [1] |
Stationary distribution | 稳态分布 | [1] |
Stationary point | 驻点 | [1] |
Statistical learning | 统计学习 | [1] |
Status feature function | 状态特征函数 | [1] |
Stochastic gradient descent | 随机梯度下降 | [1] |
Stochastic Matrix | 随机矩阵 | [1] |
Stochastic maximum likelihood | 随机最大似然 | [1] |
Stochastic Neighbor Embedding | 随机近邻嵌入 | [1] |
Stratified sampling | 分层采样 | [1] |
Structural risk | 结构风险 | [1] |
Structural risk minimization/SRM | 结构风险最小化 | [1] |
Structured variational inference | 结构化变分推断 | [1] |
Subsampling | 下采样 | [1] |
Subspace | 子空间 | [1] |
Supervised learning | 监督学习/有导师学习 | [1] |
support vector expansion | 支持向量展式 | [1] |
Support Vector Machine/SVM | 支持向量机 | [1] |
Surrogat loss | 替代损失 | [1] |
Surrogate function | 替代函数 | [1] |
Symbolic learning | 符号学习 | [1] |
Symbolism | 符号主义 | [1] |
Synset | 同义词集 | [1] |
Synthetic feature | 合成特征 | [1] |
Letter T
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Tangent plane | 切平面 | [1] |
Tangent prop | 正切传播 | [1] |
T-Distribution Stochastic Neighbour Embedding/t-SNE | T分布随机近邻嵌入 | [1] |
Tempered transition | 回火转移 | [1] |
Tensor | 张量 | [1] |
Tensor Processing Units/TPU | 张量处理单元 | [1] |
The least square method | 最小二乘法 | [1] |
Threshold | 阈值 | [1] |
Threshold logic unit | 阈值逻辑单元 | [1] |
Threshold-moving | 阈值移动 | [1] |
Tiled convolution | 平铺卷积 | [1] |
Time delay neural network | 时延神经网络 | [1] |
Time Step | 时间步骤 | [1] |
Tractable | 易处理的 | |
Tokenization | 标记化/分词 | [1] |
Training error | 训练误差 | [1] |
Training instance | 训练实例 | [1] |
Transductive learning | 直推学习 | [1] |
Transfer learning | 迁移学习/转移学习 | [1]/[5] |
Treebank | 树库 | [1] |
Trial-by-error | 试错法 | [1] |
Triangulate | 三角形化 | [1] |
Trigram | 三元语法 | [1] |
True negative | 真负例 | [1]/[5] |
True positive | 真正例 | [1]/[5] |
True Positive Rate/TPR | 真正例率 | [1] |
Turing Machine | 图灵机 | [1] |
Twice-learning | 二次学习 | [1] |
Two-dimensional array | 二维数组 | [1] |
Letter U
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Underestimation | 欠估计 | [1] |
Underfitting | 欠拟合/欠配 | [1] |
Undersampling | 欠采样 | [1] |
Understandability | 可理解性 | [1] |
Undirected graphical model | 无向图模型 | [1] |
Unequal cost | 非均等代价 | [1] |
Unit norm | 单位范数 | [1] |
Unit test | 单元测试 | [1] |
Unit variance | 单位方差 | [1] |
Unitary matrix | 酉矩阵 | [1] |
Unit-step function | 单位阶跃函数 | [1] |
Univariate decision tree | 单变量决策树 | [1] |
Unprojection | 反投影 | [1] |
Unshared convolution | 非共享卷积 | [1] |
Unsupervised learning | 无监督学习/无导师学习 | [1] |
Unsupervised layer-wise training | 无监督逐层训练 | [1] |
Upper Confidence Bounds | 上置信界限 | [1] |
Upsampling | 上采样 | [1] |
Letter V
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Vanishing Gradient Problem | 梯度消失问题 | [1] |
Variational derivative | 变分导数 | [1] |
Variational free energy | 变分自由能 | [1] |
Variational inference | 变分推断 | [1] |
VC Theory | VC维理论 | [1] |
Version space | 版本空间 | [1] |
Virtual adversarial example | 虚拟对抗样本 | [1] |
Viterbi algorithm | 维特比算法 | [1] |
Von Neumann architecture | 冯 · 诺伊曼架构 | [1] |
Letter W
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Weak learner | 弱学习器 | [1] |
Weight | 权重 | [1] |
Weight decaying | 权值衰减 | [1] |
Weight sharing | 权共享 | [1] |
Weighted voting | 加权投票法 | [1] |
Wasserstein GAN/WGAN | Wasserstein生成对抗网络 | [1] |
Within-class scatter matrix | 类内散度矩阵 | [1] |
Word embedding | 词嵌入 | [1] |
Word sense disambiguation | 词义消歧 | [1] |
Letter Z
英文/缩写 | 汉语 | 来源&扩展 |
---|---|---|
Zero mean | 零均值 | [1] |
Zero-data learning | 零数据学习 | [1] |
Zero-shot learning | 零次学习 | [1] |