人工智能专业词汇

《人工智能专业词汇》由会员分享，可在线阅读，更多相关《人工智能专业词汇（12页珍藏版）》请在装配图网上搜索。

1、Letter AAccumulated error backpropagation 累积误差逆传播Activation Function 激活函数Adaptive Resonance Theory/ART 自适应谐振理论Addictive model 加性学习Adversarial Networks 对抗网络Affine Layer 仿射层Affinity matrix 亲和矩阵Agent 代理 / 智能体Algorithm 算法Alpha-beta pruning a - B 剪枝Anomaly detection 异常检测Approximation 近似Area Under ROC Cur

2、veAUC 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Autoencoder 自编码器Automatic speech recognition自动语音识别Automatic summarizat

3、ion自动摘要Average gradient 平均梯度Average-Pooling 平均池化Letter BBackpropagation Through Time 通过时间的反向传播Backpropagation/BP 反向传播Base learner 基学习器Base learning algorithm 基学习算法Batch Normalization/BN 批量归一化Bayes decision rule 贝叶斯判定准则Bayes Model AveragingBMA贝叶斯模型平均Bayes optimal classifier 贝叶斯最优分类器Bayesian decision

4、theory 贝叶斯决策论Bayesian network 贝叶斯网络Between-class scatter matrix 类间散度矩阵Bias 偏置 / 偏差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 二分类Binomial test 二项检验Bi-partition 二分法Boltzmann machine 玻尔兹曼机Bootstrap sampling

5、自助采样法可重复采样有放回采样Bootstrapping 自助法Break-Event PointBEP 平衡点Letter CCalibration 校准Cascade-Correlation 级联相关Categorical attribute 离散属性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 类别不平衡Closed -form 闭式Cluster 簇/类/集群Cluster analysis 聚类分析Cluste

6、ring 聚类Clustering ensemble 聚类集成Co-adapting 共适应Coding matrix 编码矩阵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

7、 概念学习系统Conditional entropy 条件熵Conditional mutual information 条件互信息Conditional Probability TableCPT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Connection weight 连接权Connectionism 连结主义Consistency 一致性相合性Contingency table 列联表Continuous attribute 连续属性Conv

8、ergence 收敛Conversational agent 会话智能体Convex quadratic programming 凸二次规划Convexit y 凸f生Convolutional neural network/CNN 卷积神经网络Co-occurrence 同现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Cross entropy 交叉熵Cross validation 交叉验证Crow

9、dsourcing 众包Curse of dimensionality 维数灾难Cut point截断点Cutting plane algorithm 割平面法Letter DData mining 数据挖掘Data set 数据集Decision Boundary 决策边界Decision stump 决策树桩Decision tree 决策树判定树Deduction 演绎深度卷积生成对抗网络Deep Belief Network 深度信念网络Deep Convolutional Generative Adversarial Network/DCGANDeep learning 深度学习De

10、ep neural network/DNN 深度神经网络Deep Q-Learning 深度 Q 学习Deep Q-Network 深度 Q 网络Density estimation 密度估计Densit y- based clustering 密度聚类Differentiable neural computer 可微分神经计算机Dimensionality reduction algorithm 降维算法Directed edge 有向边Disagreement measure 不合度量Discriminative model 判别模型Discriminator 判别器Distance me

11、asure 距离度量Distance metric learning 距离度量学习Distribution 分布Divergence 散度Diversity measure 多样生度量差异生度量Domain adaption 领域自适应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Letter EEigenvalue decomposition 特征值分解Embedding 嵌入Em

12、otional 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Error Correcting Output CodesECOC 纠错输出码Error rate 错误率Error-ambiguity decomposition 误差-分歧分解 Euclidean

13、distance 欧氏距离Evolutionary computation 演化计算 Expectation-Maximization 期望最大化Expected loss 期望损失Exploding Gradient Problem 梯度爆炸问题 Exponential loss function 指数损失函数 Extreme Learning Machine/ELM 超限学习机 Letter FFactorization 因子分解False negative 假负类False positive 假正类False Positive Rate/FPR 假正例率Feature engineeri

14、ng 特征工程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Fine-tuning 微调Flipping output 翻转法Fluctuation 震荡Forward stagewise algorithm 前向分步算法Frequentist 频率主义学派Full-rank matrix 满秩矩阵Functional neuron 功能神经元Letter GGain ratio增益率Game theory 博弈论Gaussian kern

15、el function 高斯核函数Gaussian Mixture Mode I 高斯混合模型General Problem Solving 通用问题求解Generalizatio n 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 Rayleigh quotient 广义瑞利商 Generative Adversarial Networks/GAN 生成对

16、抗网络 Generative Model 生成模型Generator 生成器Genetic Algorithm/GA 遗传算法Gibbs sampling 吉布斯采样Gini index 基尼指数Global minimum 全局最小Global Optimization 全局优化Gradient boosting 梯度提升Gradient Descent 梯度下降Graph theory 图论Ground-truth 真相真实Letter HHard margin 硬间隔Hard voting 硬投票Harmonic mean 调和平均Hesse matrix 海塞矩阵Hidden dyna

17、mic 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 假设验证Letter IICML 国际机器学习会议Improved iterative scaling/IIS 改进的迭代尺度法Increme

18、ntal 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Information entropy 信息熵Information gain 信息增益Inp

19、ut layer 输入层Insensitive loss 不敏感损失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Isometric Mapping/Isomap 等度量映射Isotonic regression 等分回归Iterative Dichotomiser 迭代二分器Letter KKernel method 核方法Kernel trick 核技巧Kerne

20、lized 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 Representation 知识表征Letter LLabel 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

21、Laplacian correction 拉普拉斯修正Latent Dirichlet Allocation 隐狄利克雷分布Latent semantic analysis 潜在语义分析Latent variable 隐变量Lazy learning 懒惰学习Learner 学习器Learning by analogy 类比学习Learning rate 学习率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linear chain conditio

22、nal random field 线性链条件随机场Linear Discriminant Analysis / LDA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 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 Ter

23、m Memory/LSTM 长短期记忆Loss function 损失函数Letter MMachine translation/MT 机器翻译Macron-P 宏查准率Macron-R宏查全率Majority voting 绝对多数投票法Manifold assumption 流形假设Manifold learning 流形学习Margin theory间隔理论Marginal distribution 边际分布Marginal independence 边际独立性Marginalization 边际化Markov Chain Monte Carlo/MCMC 马尔可夫链蒙特卡罗方法Mark

24、ov Random Field 马尔可夫随机场Maximal clique 最大团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 squared error 均方误差Meta-learner 元学习器Metric learning 度量学习Micro-P 微查准率Micro-R 微查全率Minimal Description Length/MDL 最小描述长度Minimax game极小极大博弈M

25、isclassification cost 误分类成本Mixture of experts 混合专家Momentum 动量Moral graph 道德图/端正图Multi-class classification 多分类Multi-document summarization 多文档摘要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Multiple Dimensional Scaling 多维缩放Multiple linear reg

26、ression 多元线性回归Multi-response Linear Regression MLR 多响应线性回归Mutual information 互信息Letter NNaive 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Natural language generation/NLG 自然语言生成Natural language processing 自然语言处理Negative class 负类Negative correlation 负相

27、关法Negative Log Likelihood 负对数似然Neighbourhood Component Analysis/NCA 近邻成分分析Neural Machine Translation 神经机器翻译Neural Turing Machine 神经图灵机Newton method 牛顿法NIPS国际神经信息处理系统会议No Free Lunch TheoremNFL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

28、 非线性模型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Letter OObjective function 目标函数Oblique decision tree 斜决策树Occams razor奥卡姆剃刀Odds 几率Off-Policy 离策略One shot learning 一

29、次性学习One-Dependent EstimatorODE 独依赖估计On-Policy在策略Ordinal attribute 有序属性Out-of-bag estimate 包外估计Output layer 输出层Output smearing 输出调制法Overfitting 过拟合过配Oversampling 过采样Letter PPaired t-test 成对 t 检验Pairwise 成对型Pairwise Markov property 成对马尔可夫性Parameter 参数Parameter estimation 参数估计Parameter tuning 调参Parse t

30、ree 解析树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 kernel function 多项式核函数Pooling 池化Positive class 正类Positive definite matrix 正定矩阵Post-hoc tes

31、t 后续检验Post-pruning 后剪枝potential function 势函数Precision 查准率准确率Prepruning 预剪枝Principal component analysis/PCA 主成分分析Principle of multiple explanations 多释原则Prior先验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Letter QQuantized Neural Network 量子化神经网络Quantum

32、 computer量子计算机Quantum Computing量子计算Quasi Newton method 拟牛顿法Letter RRadial Basis FunctionRBF 径向基函数Random Forest Algorithm 随机森林算法Random walk 随机漫步Recall 查全率召回率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Refe

33、rence model 参考模型Regression 回归Regularization 正则化Reinforcement learning/RL 强化学习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Residual Mapping 残差映射Residual Network 残差网络Restricted Boltzmann Machine/RBM 受限玻尔兹曼机 Restricted

34、 Isometry Property/RIP 限定等距性Re-weighting 重赋权法Robustness 稳健性/鲁棒性Root node 根结点Rule Engine 规则引擎Rule learning 规则学习Letter SSaddle point 鞍点Sample space 样本空间Sampling 采样Score function 评分函数Self-Driving 自动驾驶Self-Organizing MapSOM 自组织映射 Semi-naive Bayes classifiers 半朴素贝叶斯分类器 Semi-Supervised Learning 半监督学习 semi

35、-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 Sigmoid function Sigmoid 函数 Similarity measure 相似度度量 Simulated annealing 模拟退火Simultaneous localization and mappin g 同步定位与地图构建 Singular Value Decomposition 奇异值分解Slack variables 松弛变量Smoothing 平滑Soft margin 软

36、间隔Soft margin maximization 软间隔最大化Soft voting 软投票Sparse representation 稀疏表征Sparsity 稀疏性Specialization 特化Spectral Clustering 谱聚类Speech Recognitio n 语音识另 ijSplitting variable 切分变量Squashing function 挤压函数Stability-plasticity dilemma 可塑性-稳定性困境Statistical learning 统计学习Status feature function 状态特征函Stochasti

37、c gradient descent 随机梯度下降Stratified sampling 分层采样Structural risk 结构风险Structural risk minimization/SRM 结构风险最小化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

38、集Letter TT-Distribution Stochastic Neighbour Embedding/t-SNE T - 分布随机近邻嵌入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Time Step 时间步骤Tokenization 标记化Training error 训练误差Training instance 训练示例/训练例Transductive learning

39、 直推学习Transfer learning 迁移学习Treebank 树库Tria-by-error 试错法True negative 真负类True positive 真正类True Positive Rate/TPR 真正例率Turing Machine 图灵机Twice-learnin g 二次学习Letter UUnderfitting 欠拟合欠配Undersampling 欠采样Understandability 可理解性Unequal cost 非均等代价Unit-step function 单位阶跃函数Univariate decision tree 单变量决策树Unsuper

40、vised learning 无监督学习无导师学习Unsupervised layer-wise training 无监督逐层训练Upsampling 上采样Letter VVanishing Gradient Problem 梯度消失问题Variational inference 变分推断VC Theory VC 维理论Version space 版本空间Viterbi algorithm 维特比算法Von Neumann architecture 冯诺伊曼架构Letter WWasserstein GAN/WGAN Wasserstein 生成对抗网络Weak learner 弱学习器Weight 权重Weight sharing 权共享Weighted voting 加权投票法Within-class scatter matrix 类内散度矩阵Word embedding 词嵌入Word sense disambiguation 词义消歧Letter ZZero-data learning 零数据学习Zero-shot learning 零次学习 作者：业余草来源：CSDN原文： 版权声明：本文为博主原创文章，转载请附上博文链接！