翻译专业术语表
目录
警告
本文最后更新于 2021-09-23,文中内容可能已过时。
| 英语 | 简称 | 中文 | 
|---|---|---|
| Accuracy | 精度 | |
| Activation Function | 激活函数 | |
| Adaptive Boosting | AdaBoost | AdaBoost | 
| Adaptive Gradient Algorithm | AdaGrad | AdaGrad | 
| Adaptive Moment Estimation Algorithm | Adam | Adam | 
| Affinity Matrix | 亲和矩阵 | |
| Agent | 智能体 | |
| Alpha-Beta Pruning | α-β修剪法 | |
| Anomaly Detection | 异常检测 | |
| Area Under ROC Curve | AUC | |
| Artificial Intelligence | AI | 人工智能 | 
| Artificial Neural Network | ANN | 人工神经网络 | 
| Attention Mechanism | 注意力机制 | |
| Autoencoder | AE | 自编码器 | 
| Automatic Differentiation | AD | 自动微分 | 
| Autoregressive | AR | 自回归 | 
| Back Propagation | BP | 反向传播 | 
| Bag of Words | BOW | 词袋 | 
| Bagging | 装袋 | |
| Bandit | 赌博机/老虎机 | |
| Baseline | 基准 | |
| Batch Gradient Descent | BGD | 批量梯度下降法 | 
| Batch Normalization | BN | 批量规范化 | 
| Batch Size | 批量大小 | |
| Bayes Classifier | 贝叶斯分类器 | |
| Beam Search | 束搜索 | |
| Benchmark | 基准 | |
| Bi-Directional Long-Short Term Memory | Bi-LSTM | 双向长短期记忆 | 
| Bias | 偏差/偏置 | |
| Bidirectional Recurrent Neural Network | Bi-RNN | 双向循环神经网络 | 
| Bigram | 二元语法 | |
| Binary Sparse Coding | 二值稀疏编码 | |
| Boosting Tree | 提升树 | |
| Bootstrap Sampling | 自助采样法 | |
| Bootstrapping | 自助法/自举法 | |
| Bottom-Up | 自下而上 | |
| Chebyshev Distance | 切比雪夫距离 | |
| Classification And Regression Tree | CART | 分类与回归树 | 
| Computer Vision | CV | 计算机视觉 | 
| Conditional Random Field | CRF | 条件随机场 | 
| Confidence | 置信度 | |
| Confusion Matrix | 混淆矩阵 | |
| Conjugate Gradient | 共轭梯度 | |
| Consistency Convergence | 一致性收敛 | |
| Content-Addressable Memory | CAM | 基于内容寻址的存储 | 
| Context-Specific Independences | 特定上下文独立 | |
| Contextual Bandit | 上下文赌博机/上下文老虎机 | |
| Contextualized Representation | 基于上下文的表示 | |
| Contractive Autoencoder | 收缩自编码器 | |
| Contrastive Divergence | 对比散度 | |
| Convergence | 收敛 | |
| Convex Optimization | 凸优化 | |
| Convex Quadratic Programming | 凸二次规划 | |
| Convolutional Neural Network | CNN | 卷积神经网络 | 
| Correlation Coefficient | 相关系数 | |
| Cost Function | 代价函数 | |
| Covariance | 协方差 | |
| Credit Assignment Problem | CAP | 贡献度分配问题 | 
| Cross Correlation | 互相关 | |
| Cross Entropy | 交叉熵 | |
| Cross Validation | 交叉验证 | |
| Cross-Entropy Loss Function | 交叉熵损失函数 | |
| Cumulative Distribution Function | CDF | 累积分布函数 | 
| Curvature | 曲率 | |
| Curve-Fitting | 曲线拟合 | |
| Data Mining | 数据挖掘 | |
| Decision Tree | 决策树 | |
| Deconvolution | 反卷积 | |
| Deduction | 演绎 | |
| Deep Convolutional Generative Adversarial Network | DCGAN | 深度卷积生成对抗网络 | 
| Denoising | 去噪 | |
| Derivative | 导数 | |
| Determinant | 行列式 | |
| Diagonal Matrix | 对角矩阵 | |
| Dimension Reduction | 降维 | |
| Discriminative Model | 判别式模型 | |
| Discriminator | 判别器 | |
| Distance Measure | 距离度量 | |
| Diverge | 发散 | |
| Divergence | 散度 | |
| Diversity Measure | 多样性度量/差异性度量 | |
| Down Sampling | 下采样 | |
| Dropout | 暂退法 | |
| Dual Problem | 对偶问题 | |
| Dynamic Programming | 动态规划 | |
| Early Stopping | 早停 | |
| Echo State Network | 回声状态网络 | |
| Eigendecomposition | 特征分解 | |
| Eigenvalue | 特征值 | |
| Eigenvalue Decomposition | 特征值分解 | |
| Element-Wise Product | 逐元素积 | |
| Embedding | 嵌入 | |
| Empirical Conditional Entropy | 经验条件熵 | |
| End-To-End | 端到端 | |
| Ensemble Learning | 集成学习 | |
| Entropy | 熵 | |
| Episode | 回合 | |
| Epoch | 轮 | |
| Estimation Of Mathematical Expectation | 数学期望估计 | |
| Estimator | 估计/估计量 | |
| Euclidean Distance | 欧氏距离 | |
| Euclidean Norm | 欧几里得范数 | |
| Evaluation Criterion | 评价准则 | |
| Evolution | 演化 | |
| Expectation | 期望 | |
| Expectation Maximization | EM | 期望最大化 | 
| Exploding Gradient | 梯度爆炸 | |
| Exponential Decay | 指数衰减 | |
| Extreme Learning Machine | ELM | 超限学习机 | 
| Factor | 因子 | |
| Feature Engineering | 特征工程 | |
| Feature Map | 特征图 | |
| Feature Selection | 特征选择 | |
| Feedforward | 前馈 | |
| Few-Shot Learning | 少试学习 | |
| Filter | 滤波器 | |
| Fine-Tuning | 微调 | |
| Forward Propagation | 前向传播/正向传播 | |
| Frobenius Norm | Frobenius范数 | |
| Full Padding | 全填充 | |
| Gated Recurrent Unit | GRU | 门控循环单元 | 
| Gated RNN | 门控RNN | |
| Gaussian Mixture Model | GMM | 高斯混合模型 | 
| Generalization Ability | 泛化能力 | |
| Generalization Error Bound | 泛化误差上界 | |
| Generalize | 泛化 | |
| Generalized Lagrange Function | 广义拉格朗日函数 | |
| Generalized Rayleigh Quotient | 广义瑞利商 | |
| Generative Adversarial Network | GAN | 生成对抗网络 | 
| Generative Model | 生成式模型 | |
| Generator | 生成器 | |
| Genetic Algorithm | 遗传算法 | |
| Gini Index | 基尼指数 | |
| Global Markov Property | 全局马尔可夫性 | |
| Gradient | 梯度 | |
| Gradient Clipping | 梯度截断 | |
| Gradient Descent | 梯度下降 | |
| Graph Convolutional Network | GCN | 图卷积神经网络 | 
| Graph Neural Network | GNN | 图神经网络 | 
| Graphical Model | GM | 图模型 | 
| Grid Search | 网格搜索 | |
| Ground Truth | 真实值 | |
| Hidden Markov Model | HMM | 隐马尔可夫模型 | 
| Hierarchical Clustering | 层次聚类 | |
| 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 | |
| Incremental Learning | 增量学习 | |
| Independent and Identically Distributed | I.I.D. | 独立同分布 | 
| Induction | 归纳 | |
| Inductive Bias | 归纳偏好 | |
| Inference | 推断 | |
| Information Entropy | 信息熵 | |
| Information Gain | 信息增益 | |
| Information Retrieval | 信息检索 | |
| Inner Product | 内积 | |
| Internet of Things | IoT | 物联网 | 
| Inverse Matrix | 逆矩阵 | |
| Joint Probability Distribution | 联合概率分布 | |
| K-Armed Bandit | k-摇臂老虎机 | |
| K-Fold Cross Validation | k折交叉验证 | |
| Karush-Kuhn-Tucker Condition | KKT条件 | |
| Kernelized Linear Discriminant Analysis | KLDA | 核线性判别分析 | 
| KL Divergence | KL散度 | |
| Knowledge Distillation | 知识蒸馏 | |
| Label | 标签/标记 | |
| Lagrange Duality | 拉格朗日对偶性 | |
| Lagrange Multiplier | 拉格朗日乘子 | |
| Latent Semantic Analysis | LSA | 潜在语义分析 | 
| Latent Variable | 潜变量/隐变量 | |
| 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 | |
| Learning By Analogy | 类比学习 | |
| Learning Rate | 学习率 | |
| Least Square Method | LSM | 最小二乘法 | 
| Likelihood | 似然 | |
| Linear Dependence | 线性相关 | |
| Linear Discriminant Analysis | LDA | 线性判别分析 | 
| Linear Regression | 线性回归 | |
| Local Representation | 局部式表示/局部式表征 | |
| Log Likelihood | 对数似然函数 | |
| Log-Likelihood | 对数似然 | |
| Logistic Regression | LR | 对数几率回归 | 
| Logit | 对数几率 | |
| Long Short Term Memory | LSTM | 长短期记忆 | 
| Loss Function | 损失函数 | |
| Macron-Recall | Macron-R | 宏查全率 | 
| Manhattan Distance | 曼哈顿距离 | |
| Manifold | 流形 | |
| 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 | MCMC | 马尔可夫链蒙特卡罗 | 
| Markov Decision Process | MDP | 马尔可夫决策过程 | 
| Markov Random Field | MRF | 马尔可夫随机场 | 
| Mask | 掩码 | |
| 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 | MLE | 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 | |
| Message Passing | 消息传递 | |
| Metric Learning | 度量学习 | |
| Micro-Recall | Micro-R | 微查全率 | 
| Minibatch | 小批量 | |
| Minimax Game | 极小极大博弈 | |
| Minkowski Distance | 闵可夫斯基距离 | |
| Momentum Method | 动量法 | |
| Monte Carlo Method | 蒙特卡罗方法 | |
| 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-Layer Perceptron | MLP | 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 | |
| Mutual Information | 互信息 | |
| N-Gram | N元 | |
| N-Gram Model | N元模型 | |
| Naive Bayes | NB | 朴素贝叶斯 | 
| Natural Language Generation | NLG | 自然语言生成 | 
| Natural Language Processing | NLP | 自然语言处理 | 
| Natural Language Understanding | NLU | 自然语言理解 | 
| Nearest Neighbor | 最近邻 | |
| Net Input | 净输入 | |
| Newton Method | 牛顿法 | |
| No Free Lunch Theorem | NFL | 没有免费午餐定理 | 
| Norm | 范数 | |
| Normal Distribution | 正态分布 | |
| Normalization | 规范化 | |
| Object Detection | 目标检测 | |
| Odds | 几率 | |
| Off-Policy | 异策略 | |
| On-Policy | 同策略 | |
| 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 | |
| Outlier | 异常点 | |
| Overfitting | 过拟合 | |
| Oversampling | 过采样 | |
| Padding | 填充 | |
| Parameter Estimation | 参数估计 | |
| Parameter Tuning | 调参 | |
| Parametric ReLU | PReLU | 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 | |
| Partition Function 配分函数 | ||
| Perceptron | 感知机 | |
| Performance Measure | 性能度量 | |
| Perplexity | 困惑度 | |
| Pervasive Learning | 普适学习 | |
| Policy | 策略 | |
| 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 | |
| Precision | 查准率/准确率 | |
| Prepruning | 预剪枝 | |
| Principal Component Analysis | PCA | 主成分分析 | 
| Prior | 先验 | |
| Singular Value Decomposition | SVD | 奇异值分解 | 
| Support Vector Machines | SVM | 支持向量机 | 
| Validation Set | 验证集 | |
| Vanishing Gradient | 梯度消失 | |
| Vapnik-Chervonenkis Dimension | VC维 | |
| Variance | 方差 | |
| Variance Reduction | 方差减小 | |
| Variance Scaling | 方差缩放 | |
| Variational Autoencoder | VAE | 变分自编码器 | 
| Vectorization | 向量化 | |
| Wasserstein Distance | Wasserstein距离 | |
| Wasserstein GAN | WGAN | Wasserstein生成对抗网络 | 
| Word Embedding | 词嵌入 | |
| Word Sense Disambiguation | 词义消歧 | |
| Zero-Shot Learning | 零试学习 |