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-剪枝Anomaly detection异常检测Approximation近似Area Under ROC CurveAUCRoc 曲线下面积Art
2、ificial 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 summarization自动摘要Average gradient平
3、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 theory贝叶斯决策论Bayesian network贝叶斯网络
4、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自助采样法可重复采样有放回采样Bootstrapping自助法Break-Event Po
5、intBEP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Clustering聚类Clustering ensemble聚类集成Co-adapting共适应Coding matrix编
6、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 LearningSystem/CLS概念学习系统Conditional entropy条件熵Conditional mutual information条件互信息Condition
7、al 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Convergence收敛Conversational agent会话智能体Convex quadratic programming凸二次规划Convexity凸性Convol
8、utional 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Crowdsourcing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
9、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Deep Belief Network深度信念网络Deep Convolutional Generative Adversarial Network/DCGAN深度卷积生成对抗网络Deep learning深度学习Deep 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Density-based clust
10、ering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 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Downsampling
11、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 mo
12、del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 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Ext
13、reme 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 engineering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 al
14、gorithm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 kernel function高斯核函数Gaussian Mixture Model高斯混合模型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
15、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-t
16、ruth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 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Hypothesi
17、s 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 Progr
18、ammingILP归纳逻辑程序设计Information entropy信息熵Information gain信息增益Input 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 Dichotomis
19、er迭代二分器Letter KKernel method核方法Kernel trick核技巧Kernelized Linear Discriminant AnalysisKLDA核线性判别分析K-fold cross validationk 折交叉验证k 倍交叉验证K-Means ClusteringK 均值聚类K-Nearest Neighbours Algorithm/KNNK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 mult
20、iplier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
21、留一法linear chain conditional random field线性链条件随机场Linear Discriminant AnalysisLDA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 oddslogit对数几率Logistic RegressionLogistic 回归Log-likelihood对数似然Log-linear regression对数线性回归Long-S
22、hort Term 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Markov
23、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Misclassification
24、 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 regression多元线性回归Multi-response
25、 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负相关法Negative Log Likelihood负对数似然Neighbou
26、rhood 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非线性模型Non-metric distance非度量距离Non-negative matr
27、ix 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一次性学习One-Dependent EstimatorODE独依赖估计On-Policy在策略Ordinal attri
28、bute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 tree解析树Particle Swarm Optimization/PSO粒子群优化算法Part-of-speech tagging词性标注Per
29、ceptron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 test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 compon
30、ent 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 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Ra
31、ndom 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Reference 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Repres
32、enter 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 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 po
33、int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-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 functionSigmoid 函数Similarity measure相似度度
34、量Simulated annealing模拟退火Simultaneous localization and mapping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 Recognition语音识别Splitting var
35、iable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Stochastic 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
36、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Letter TT-Distribution Stochastic Neighbour Embedding/t-SNET 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Threshol
37、d-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-learning二次学习Letter UUnderfitting欠拟合欠配Undersampling欠采样Understandab
38、ility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Unsupervised 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 TheoryVC维理论Version space版本空间Viterbi algorithm维特比算法Von Neumann archite
39、cture冯 诺伊曼架构Letter WWasserstein GAN/WGANWasserstein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零次学习模式识别计算机硬件的迅速发展,计算机应用领域的不断开拓,急切地要求计算机能更有效地感知诸如声音、文字
40、、图象、温度、震动等等信息资料,模式识别便得到迅速发展。模式(Pattern)一词的本意是指模式(Pattern)一词的本意是指完美无缺的供模仿的一些标本。模式识别就是指识别出给定物体所模仿的标本。人工智能所研究的模式识别是指用计算机代替人类或帮助人类感知模式,是对人类感知外界功能的模拟,研究的是计算机模式识别系统,也就是使一个计算机系统具有模拟人类通过感官接受外界信息、识别和理解周围环境的感知能力。 模式识别是一个不断发展的新学科,它的理论基础和研究范围也在不断发展。随着生物医学对人类大脑的初步认识,模拟人脑构造的计算机实验即人工神经网络方法早在50年代末、60年代初就已经开始。至今,在模式
41、识别领域,神经网络方法已经成功地用于手写字符的识别、汽车牌照的识别、指纹识别、语音识别等方面。目前模式识别学科正处于大发展的阶段,随着应用范围的不断扩大,随着计算机科学的不断进步,基于人工神经网络的模式识别技术,在90年代将有更大的发展。机器视觉 机器视觉或计算机视觉已从模式识别的一个研究领域发展为一门独立的学科。在视觉方面,已经给计算机系统装上电视输入装置以便能够看见周围的东西。视觉是感知问题之一。在人工智能中研究的感知过程通常包含一组操作。例如,可见的景物由传感器编码,并被表示为一个灰度数值的矩阵。这些灰度数值由检测器加以处理。检测器搜索主要图象的成分,如线段、简单曲线和角度等。这些成分又
42、被处理,以便根据景物的表面和形状来推断有关景物的三维特性信息。机器视觉的前沿研究领域包括实时并行处理、主动式定性视觉、动态和时变视觉、三维景物的建模与识别、实时图象压缩传输和复原、多光谱和彩色图象的处理与解释等。机器视觉已在机器人装配、卫星图象处理、工业过程监控、飞行器跟踪和制导以及电视实况转播等领域获得极为广泛的应用。 5.智能控制 人工智能的发展促进自动控制向智能控制发展。智能控制是一类无需(或需要尽可能少的)人的干预就能够独立地驱动智能机器实现其目标的自动控制。或者说,智能控制是驱动智能机器自主地实现其目标的过程。随着人工智能和计算机技术的发展,已可能把自动控制和人工智能以及系统科学的某些分支结合起来,建立一种适用于复杂系统的控制理论和技术。智能控制正是在这种条件下产生的。它是自动控制的最新发展阶段,也是用计算机模拟人类智能的一个重要研究领域。1965年,傅京孙首先提出把人工智能的启发式推理规则用于学习控制系统。十多年后,建立实用智能控制系统的技术逐渐成熟。1971年,傅京孙提出把人工智能与自动控制结合起来的思想。1977年,美国萨里迪斯提出把人工智能、控制论和运筹学结合起来的思想。1986年,中国蔡自兴提出把人工智能、控制论、信息论和运筹学结合起来的思想。按照这些结构理论已经研究出一些智能控制的理论和技术,用来构造用于不同领域的智能控制系统。智能控制的核心在高层控制,
版权声明:以上文章中所选用的图片及文字来源于网络以及用户投稿,由于未联系到知识产权人或未发现有关知识产权的登记,如有知识产权人并不愿意我们使用,如有侵权请立即联系:2622162128@qq.com ,我们立即下架或删除。
Copyright© 2022-2024 www.wodocx.com ,All Rights Reserved |陕ICP备19002583号-1
陕公网安备 61072602000132号 违法和不良信息举报:0916-4228922