Summary
The second part of artificial intelligence term translation, including words starting with E, F, G, H!
E
| English term | Chinese translation | commonly used abbreviations | Remark |
|---|---|---|---|
| Eager Learning | eager to learn | ||
| Early Stopping | early stop | ||
| Earth-Mover’s Distance | bulldozer distance | EMD | |
| Echo State Network | echo state network | ||
| Edge | side | ||
| Edge Device | edge device | ||
| Effective Capacity | effective capacity | ||
| Eigendecomposition | Eigen decomposition | ||
| Eigenvalue | Eigenvalues | ||
| Eigenvalue Decomposition | Eigenvalue Decomposition | ||
| Elastic Net Regularization | Elastic Net Regularization | ||
| Elastic Weight Consolidation | Elastic Weight Consolidation | ||
| Element-Wise Product | element-wise product | ||
| Elementary Basis Vectors | base unit vector | ||
| Ellipsoid Method | ball method | ||
| Embedding | embed | ||
| Embedding Lookup Table | embedded table | ||
| Emotional Analysis | sentiment analysis | ||
| Empirical Conditional Entropy | Empirical Conditional Entropy | ||
| Empirical Distribution | experience distribution | ||
| Empirical Entropy | experience entropy | ||
| Empirical Error | empirical error | ||
| Empirical Frequency | empirical frequency | ||
| Empirical Loss | experience loss | ||
| Empirical Risk | empirical risk | ||
| Empirical Risk Minimization | Empirical Risk Minimization | ERM | |
| Encoder | Encoder | ||
| Encoder-Decoder | encoder-decoder (model) | ||
| Encoding | coding | ||
| End-To-End | end to end | ||
| End-To-End Learning | end-to-end learning | ||
| End-To-End Memory Network | end-to-end memory network | Memn2N | |
| Energy Function | energy function | ||
| Energy Gap | energy difference | ||
| Energy-Based Model | energy-based model | ||
| Ensemble | integrated | ||
| Ensemble Learning | integrated learning | ||
| Ensemble Pruning | 集成修剪 | ||
| Entropy | 熵 | ||
| Entropy Encoding | 熵编码 | ||
| Environment | 环境 | ||
| Episode | 回合 | ||
| Episodic Task | 回合式任务 | ||
| Epoch | 轮 | ||
| Equal-Width Convolution | 等宽卷积 | ||
| Equality Constraint | 等式约束 | ||
| Equilibrium Distribution | 均衡分布 | ||
| Equivariance | 等变 | ||
| Equivariant Representations | 等变表示 | ||
| Error | 误差 | ||
| Error Backpropagation Algorithm | 误差反向传播算法 | ||
| Error Backpropagation | 误差反向传播 | ||
| Error Bar | 误差条 | ||
| Error Correcting Output Codes | 纠错输出编码 | ECOC | |
| Error Function | 误差函数 | ||
| Error Metric | 误差度量 | ||
| Error Rate | 错误率 | ||
| Error-Ambiguity Decomposition | 误差－分歧分解 | ||
| Estimation Error | 估计误差 | ||
| 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 | ||
| Euclidean Space | 欧氏空间 | ||
| Euler-Lagrange Equation | 欧拉-拉格朗日方程 | ||
| Evaluation Criterion | 评价准则 | ||
| Evidence | 证据 | ||
| Evidence Lower Bound | 证据下界 | ELBO | |
| Evolution | 演化 | ||
| Evolutionary Computation | 演化计算 | ||
| Exact | 确切的 | ||
| Exact Inference | 精确推断 | ||
| Example | 样例 | ||
| Excess Error | 额外误差 | ||
| Exchangeable | 可交换的 | ||
| Expectation | 期望 | ||
| Expectation Maximization Algorithm | 期望极大算法 | ||
| Expectation Maximization | 期望最大化 | EM | |
| Expectation Step | E步 | ||
| Expected Error | 期望错误 | ||
| Expected Loss | 期望损失 | ||
| Expected Return | 期望回报 | ||
| Expected Risk | 期望风险 | ||
| Expected Value | 期望值 | ||
| Experience | 经验 | ||
| Experience Replay | 经验回放 | ||
| Expert Network | 专家网络 | ||
| Expert System | 专家系统 | ||
| Explaining Away | 相消解释 | ||
| Explaining Away Effect | 相消解释作用 | ||
| Explanatory Factort | 解释因子 | ||
| Explicit Density Model | 显式密度模型 | ||
| Exploding Gradient | 梯度爆炸 | ||
| Exploitation | 利用 | ||
| Exploration | 探索 | ||
| Exploration-Exploitation Dilemma | 探索-利用窘境 | ||
| Exponential Decay | 指数衰减 | ||
| Exponential Distribution | 指数分布 | ||
| Exponential Linear Unit | 指数线性单元 | ELU | |
| Exponential Loss | 指数损失 | ||
| Exponential Loss Function | 指数损失函数 | ||
| Exponentially Weighted Moving Average | 指数加权移动平均 | ||
| Exposure Bias | 曝光偏差 | ||
| External Memory | 外部记忆 | ||
| Extreme Learning Machine | 超限学习机 | ELM | |
| Eigenfunction | 特征函数 | ||
| Electronegativity | 电负性 | ||
| Elman | 埃尔曼 | ||
| Empirical Models | 经验模型 | ||
| Energy Derivatives | 能源衍生品 | 在DP模型中：能量的导数 | |
| Energy Potentials | 能量潜力 | ||
| Ensemble Methods | 集成方法 | ||
| Entity Normalisation | 实体规范化 | ||
| Ethical Considerations | 道德考虑 | ||
| Euclidean Distances | 欧几里得距离 | ||
| Evolutionary Algorithms | 进化算法 | EA | |
| Evolutionary Method | 进化方法 | ||
| Exchange–Correlation | 交换关联（的能量/泛函） | ||
| Excited-State Potentials | 激发态能量 | ||
| Expected Reduction In Distortion | 符合预期的失真减少 | ERD | |
| Experimental Validation Data | 实验验证数据 | ||
| Expert Systems | 专家系统 | ESS | |
| Extended-Connectivity Circular Fingerprint | 扩展连接环形指纹 | ECFP | |
| Extraction Techniques | 提取技术 |
F
| 英文术语 | 中文翻译 | 常用缩写 | 备注 |
|---|---|---|---|
| F Measure | F值 | ||
| F-Score | F分数 | ||
| Factor | 因子 | ||
| Factor Analysis | 因子分析 | ||
| Factor Graph | 因子图 | ||
| Factor Loading | 因子负荷量 | ||
| Factorization | 因子分解 | ||
| Factorized | 分解的 | ||
| Factors of Variation | 变差因素 | ||
| False Negative | 假负例 | ||
| False Positive | 假正例 | ||
| False Positive Rate | 假正例率 | FPR | |
| Fast Dropout | 快速暂退法 | ||
| Fast Persistent Contrastive Divergence | 快速持续性对比散度 | ||
| Fault-Tolerant Asynchronous Training | 容错异步训练 | ||
| Feasible | 可行 | ||
| Feature | 特征 | ||
| Feature Engineering | 特征工程 | ||
| Feature Extraction | 特征抽取 | ||
| Feature Extractor | 特征提取器 | ||
| Feature Function | 特征函数 | ||
| Feature Map | 特征图 | ||
| Feature Scaling Transform | 特征尺度变换 | ||
| Feature Selection | 特征选择 | ||
| Feature Space | 特征空间 | ||
| Feature Vector | 特征向量 | ||
| Featured Learning | 特征学习 | ||
| Feedback | 反馈 | ||
| Feedforward | 前馈 | ||
| Feedforward Classifier | 前馈分类器 | ||
| Feedforward Network | 前馈网络 | ||
| Feedforward Neural Network | 前馈神经网络 | FNN | |
| Few-Shot Learning | 少试学习 | ||
| Fidelity | 逼真度 | ||
| Field Programmable Gated Array | 现场可编程门阵列 | ||
| Filter | 滤波器 | ||
| Filter Method | 过滤式方法 | ||
| Fine-Tuning | 微调 | ||
| Finite Difference | 有限差分 | ||
| First Layer | 第一层 | ||
| First-Order Method | 一阶方法 | ||
| First-Order Rule | 一阶规则 | ||
| Fisher Information Matrix | Fisher信息矩阵 | ||
| Fixed Point Equation | 不动点方程 | ||
| Fixed-Point Arithmetic | 不动点运算 | ||
| Flat Minima | 平坦最小值 | ||
| Flip | 翻转 | ||
| Flipping Output | 翻转法 | ||
| Float-Point Arithmetic | 浮点运算 | ||
| Fluctuation | 振荡 | ||
| Focus Attention | 聚焦式注意力 | ||
| Folk Theorem | 无名氏定理 | ||
| Forget Gate | 遗忘门 | ||
| Forward | 前向 | ||
| Forward KL Divergence | 前向KL散度 | ||
| Forward Mode Accumulation | 前向模式累加 | ||
| Forward Propagation | 前向传播/正向传播 | ||
| Forward Search | 前向搜索 | ||
| Forward Stagewise Algorithm | 前向分步算法 | ||
| Forward-Backward Algorithm | 前向-后向算法 | ||
| Fourier Transform | 傅立叶变换 | ||
| Fovea | 中央凹 | ||
| Fractionally Strided Convolution | 微步卷积 | ||
| Free Energy | 自由能 | ||
| Frequentist | 频率主义学派 | ||
| Frequentist Probability | 频率派概率 | ||
| Frequentist Statistics | 频率派统计 | ||
| Frobenius Norm | Frobenius 范数 | ||
| Full | 全 | ||
| Full Conditional Distribution | 满条件分布 | ||
| Full Conditional Probability | 全条件概率 | ||
| Full Padding | 全填充 | ||
| Full Singular Value Decomposition | 完全奇异值分解 | ||
| Full-Rank Matrix | 满秩矩阵 | ||
| Fully Connected Layer | 全连接层 | ||
| Fully Connected Neural Network | 全连接神经网络 | FCNN | |
| Fully Convolutional Network | 全卷积网络 | FCN | |
| Function | 函数 | ||
| Functional | 泛函 | ||
| Functional Derivative | 泛函导数 | ||
| Functional Margin | 函数间隔 | ||
| Functional Neuron | 功能神经元 | ||
| Faber-Christensen-Huang-Lilienfeld | Faber-Christensen-Huang-Lilienfeld | FCHL | 四个人提出的化学结构量子机器学习方法 |
| Facial Recognition | 面部识别 | ||
| FAIR Data Principles | FAIR数据原则 | Findability可找寻 Accessibility可访问 Interoperability可交互 Reuse可再用 | |
| False Negatives | 假阴性 | FNs | |
| False Positives | 假阳性 | FPs | |
| Fchl Representation | Fchl 表示 | ||
| Feature Binarization | 特征二值化 | ||
| Feature Transform | 特征变换 | ||
| Feature Vectors | 特征向量 | ||
| Features | 特征 | ||
| Feed Back | 反馈 | ||
| Feed-Forward Neural Networks | 前馈神经网络 | FFNN | |
| Feedback Structure | 反馈结构 | ||
| Final Evaluation | 最终评估 | ||
| Findable, Accessible, Interoperable, Reusable | 可查找、可访问、可互操作、可重用 | FAIR | |
| First-Principles | 第一性原理 | ||
| Flow Rate | 流速 | ||
| Forward Cross-Validation | 前向交叉验证 | ||
| Forward Prediction | 前向预测 | ||
| Forward Reaction Prediction | 前向反应预测 | ||
| Fuzzy Logic | 模糊逻辑 | FL | |
| Fuzzy Neural Networks | 模糊神经网络 | FNN |
G
| 英文术语 | 中文翻译 | 常用缩写 | 备注 |
|---|---|---|---|
| Gabor Function | Gabor函数 | ||
| Gain Ratio | 増益率 | ||
| Game Payoff | 博弈效用 | ||
| Game Theory | 博弈论 | ||
| Gamma Distribution | Gamma分布 | ||
| Gate | 门 | ||
| Gate Controlled RNN | 门控循环神经网络 | ||
| Gated | 门控 | ||
| Gated Control | 门控 | ||
| Gated Recurrent Net | 门控循环网络 | GRN | |
| Gated Recurrent Unit | 门控循环单元 | GRU | |
| Gated RNN | 门控RNN | ||
| Gater | 选通器 | ||
| Gating Mechanism | 门控机制 | ||
| Gaussian Distribution | 高斯分布 | ||
| Gaussian Error Linear Unit | 高斯误差线性单元 | GELU | |
| Gaussian Kernel | 高斯核 | ||
| Gaussian Kernel Function | 高斯核函数 | ||
| Gaussian Mixture Model | 高斯混合模型 | GMM | |
| Gaussian Mixtures | 高斯混合（模型） | ||
| Gaussian Output Distribution | 高斯输出分布 | ||
| Gaussian Process | 高斯过程 | GP | |
| Gaussian Process Regression | 高斯过程回归 | GPR | |
| Gaussian RBM | 高斯RBM | ||
| Gaussian-Bernoulli RBM | 高斯-伯努利RBM | ||
| General Problem Solving | 通用问题求解 | ||
| General Purpose GPU | 通用GPU | ||
| 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 Bregman Divergence | 一般化 Bregman 散度 | ||
| Generalized Expectation Maximization | 广义期望极大 | GEM | |
| Generalized Function | 广义函数 | ||
| Generalized Lagrange Function | 广义拉格朗日函数 | ||
| Generalized Lagrangian | 广义拉格朗日 | ||
| Generalized Linear Model | 广义线性模型 | ||
| Generalized Pseudolikelihood | 广义伪似然 | ||
| Generalized Pseudolikelihood Estimator | 广义伪似然估计 | ||
| Generalized Rayleigh Quotient | 广义瑞利商 | ||
| Generalized Score Matching | 广义得分匹配 | ||
| Generative Adversarial Framework | 生成式对抗框架 | ||
| Generative Adversarial Network | 生成对抗网络 | ||
| Generative Approach | 生成方法 | ||
| Generative Model | 生成式模型 | ||
| Generative Modeling | 生成式建模 | 机器学习 | |
| Generative Moment Matching Network | 生成矩匹配网络 | ||
| Generative Pre-Training | 生成式预训练 | GPT | |
| Generative Stochastic Network | 生成随机网络 | ||
| Generative Weight | 生成权重 | ||
| Generator | 生成器 | ||
| Generator Network | 生成器网络 | ||
| Genetic Algorithm | 遗传算法 | GA | 机器学习 |
| Geometric Margin | 几何间隔 | ||
| Giant Magnetoresistance | 巨磁阻 | ||
| Gibbs Distribution | 吉布斯分布 | ||
| Gibbs Sampling | 吉布斯采样/吉布斯抽样 | ||
| Gibbs Steps | 吉布斯步数 | ||
| Gini Index | 基尼指数 | ||
| Global Contrast Normalization | 全局对比度规范化 | ||
| Global Markov Property | 全局马尔可夫性 | ||
| Global Minima | 全局极小值 | ||
| Global Minimizer | 全局极小解 | ||
| Global Minimum | 全局最小 | ||
| Global Optimization | 全局优化 | ||
| Gradient | 梯度 | ||
| Gradient Ascent | 梯度上升 | ||
| Gradient Ascent Method | 梯度上升法 | ||
| Gradient Boosting | 梯度提升 | ||
| Gradient Boosting Tree | 梯度提升树 | ||
| Gradient Clipping | 梯度截断 | ||
| Gradient Descent | 梯度下降 | 机器学习 | |
| Gradient Descent In One-Dimensional Space | 一维梯度下降 | ||
| Gradient Descent Method | 梯度下降法 | ||
| Gradient Energy Distribution | 梯度能量分布 | ||
| Gradient Estimation | 梯度估计 | ||
| Gradient Exploding Problem | 梯度爆炸问题 | ||
| Gradient Field | 梯度场 | ||
| Gradual Warmup | 逐渐预热 | ||
| Gram Matrix | Gram 矩阵 | ||
| Graph | 图 | ||
| Graph Analytics | 图分析 | ||
| Graph Attention Network | 图注意力网络 | GAT | |
| Graph Convolutional Network | 图卷积神经网络/图卷积网络 | GCN | |
| Graph Neural Network | 图神经网络 | GNN | |
| Graph Theory | 图论 | ||
| Graphical Model | 图模型 | GM | |
| Graphics Processing Unit | 图形处理器 | ||
| Greedy | 贪心 | ||
| Greedy Algorithm | 贪心算法 | ||
| Greedy Layer-Wise Pretraining | 贪心逐层预训练 | ||
| Greedy Layer-Wise Training | 贪心逐层训练 | ||
| Greedy Layer-Wise Unsupervised Pretraining | 贪心逐层无监督预训练 | ||
| Greedy Search | 贪心搜索 | ||
| Greedy Supervised Pretraining | 贪心监督预训练 | ||
| Greedy Unsupervised Pretraining | 贪心无监督预训练 | ||
| Grid Search | 网格搜索 | ||
| Grid World | 网格世界 | ||
| Ground Truth | 真实值 | ||
| Growth Function | 增长函数 | ||
| Ga-Based Approaches | 基于遗传算法的方法 | ||
| Garbage In, Garbage Out | 无用数据入、无用数据出 | GIGO | |
| Gas-Phase Networks | 气相网络 | ||
| Gaussian Kernels | 高斯核 | ||
| Gaussian-Type Structure Descriptors | 高斯型结构描述符 | GTSD | |
| General Intelligence | 通用智能 | GI | |
| Generalized Gradient Approximation | 广义梯度近似 | GGA | |
| Generative Adversarial Networks | 生成对抗网络 | GAN | 机器学习 |
| Gradient Boosting Decision Tree | 梯度提升决策树 | GBDT | |
| Gradient-Based | 基于梯度的 | ||
| Grain-Surface Networks | 粒面网络 | ||
| Graph Convolutional | 图卷积 | GC | |
| Graph Models | 图模型 | ||
| Graph Neural Networks | 图神经网络 | GNNS | |
| Graph-Based | 基于图形 | ||
| Graph-Based Models | 基于图的模型 | ||
| Graph-Based Neural Networks | 基于图的神经网络 | ||
| Graph-Based Representation | 基于图的表示 | GB-GA | |
| Graph-Convolutional Neural Network | 图卷积神经网络 | ||
| Graphics Processing Units | 图形处理器 | ||
| Gravimetric Polymerization Degree | 比重聚合度 |
H
| 英文术语 | 中文翻译 | 常用缩写 | 备注 |
|---|---|---|---|
| Hadamard Product | Hadamard积 | ||
| Hamming Distance | 汉明距离 | ||
| Hard Attention | 硬性注意力 | ||
| Hard Clustering | 硬聚类 | ||
| Hard Margin | 硬间隔 | ||
| Hard Margin Maximization | 硬间隔最大化 | ||
| Hard Mixture Of Experts | 硬专家混合体 | ||
| Hard Tanh | 硬双曲正切函数 | ||
| Hard Target | 硬目标 | ||
| Hard Voting | 硬投票 | ||
| Harmonic Mean | 调和平均 | ||
| Harmonium | 簧风琴 | ||
| Harmony | Harmony | ||
| Harris Chain | 哈里斯链 | ||
| Hausdorff Distance | 豪斯多夫距离 | ||
| Hebbian Rule | 赫布法则 | ||
| Hebbian Theory | 赫布理论 | ||
| Helmholtz Machine | Helmholtz机 | ||
| Hesse Matrix | 海赛矩阵 | ||
| Hessian | Hessian | ||
| Hessian Matrix | 黑塞矩阵 | ||
| Heterogeneous Information Network | 异质信息网络 | HIN | |
| Heteroscedastic | 异方差 | ||
| Hidden Dynamic Model | 隐动态模型 | ||
| Hidden Layer | 隐藏层 | ||
| Hidden Markov Model | 隐马尔可夫模型 | HMM | |
| Hidden State | 隐状态 | ||
| Hidden Unit | 隐藏单元 | ||
| Hidden Variable | 隐变量 | ||
| Hierarchical Clustering | 层次聚类 | ||
| Hierarchical Reinforcement Learning | 分层强化学习 | HRL | |
| Hierarchical Softmax | 层序Softmax/层序软最大化 | ||
| Hilbert Space | 希尔伯特空间 | ||
| Hill Climbing | 爬山 | ||
| Hinge Loss Function | 合页损失函数/Hinge损失函数 | ||
| Histogram Method | 直方图方法 | ||
| Hold-Out | 留出法 | ||
| Homogeneous | 同质 | ||
| Hopfield Network | Hopfield网络 | ||
| Huffman Coding | 霍夫曼编码 | ||
| Hybrid Computing | 混合计算 | ||
| Hyperbolic Tangent Function | 双曲正切函数 | ||
| Hyperparameter | 超参数 | ||
| Hyperparameter Optimization | 超参数优化 | ||
| Hyperplane | 超平面 | 数学 | |
| Hypothesis | 假设 | ||
| Hypothesis Space | 假设空间 | ||
| Hypothesis Test | hypothetical test | ||
| Hamiltonian Matrix | Hamiltonian matrix | physics | |
| Hamiltonian Operator | Hamiltonian | physics | |
| Heterogeneous Data | heterogeneous data | ||
| Hidden Layers | hidden layer | ||
| High Data Throughput | high data throughput | ||
| High Throughput | high throughput | HT | |
| High Throughput Screening | High-throughput screening | HTS | |
| High Variance Models | high variance model | ||
| High-Dimensional Data | high dimensional data | ||
| High-Dimensional NN | High Dimensional Neural Network | HDNN | |
| High-Dimensional Objects | high-dimensional objects | ||
| High-Throughput | high throughput | ||
| Higher-Dimensional Space | high dimensional space | math | |
| Higher-Dimensional Spectral Space | high-dimensional spectral space | ||
| Homogenization | Homogenization | ||
| Homomorphic Encryption | homomorphic encryption | ||
| Human Face Recognition | face recognition | machine learning | |
| Human-Encoded | manually coded | ||
| Hybrid Model | mixed model | ||
| Hybrid Technique | hybrid technology | HM | |
| Hybrid-Neural Model | hybrid neural model | ||
| Hyperparameter Opimization | hyperparameter optimization | ||
| Hyperparameters | hyperparameters | machine learning | |
| Hyperplanes Separate | hyperplane separation |