机器学习课程术语表

简介

这里收录了机器学习课程用到的相关术语，可能不全，欢迎补齐，email：jerytang.as@gmail.com

机器学习基础

英文	中文	相关学者	相关论文
Supervised Learning	监督学习	Michael I. Jordan 更多	Overview of Supervised Learning 更多
Unsupervised Learning	无监督学习	Andrew Y. Ng(吴恩达) 更多	Building high-level features using large scale unsupervised learning 更多
Semi-supervised Learning	半监督学习	Zhihua Zhou(周志华) 更多	Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions 更多
Reinforcement Learning	强化学习	Richard S. Sutton 更多	Reinforcement Learning: An Introduction 更多
Active Learning	主动学习	Jaime G. Carbonell 更多	Support vector machine active learning with applications to text classification 更多
Online Learning	在线学习	Steven HOI 更多	Adaptive Subgradient Methods for Online Learning and Stochastic Optimization 更多
Transfer Learning	迁移学习	Qiang Yang(杨强) 更多	Boosting for transfer learning 更多
Automated Machine Learning (AutoML)	自动机器学习	Michael Muller 更多	Efficient and Robust Automated Machine Learning 更多
Representation Learning	表示学习	Geoffrey E. Hinton 更多	InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets 更多
Minkowski distance	闵可夫斯基距离	Rudolf Mathar 更多	Fuzzy clustering with squared Minkowski distances 更多
Gradient Descent	梯度下降	Nathan Srebro 更多	Learning to rank using gradient descent 更多
Stochastic Gradient Descent	随机梯度下降	Pu Zhou(周朴) 更多	Large-Scale Machine Learning with Stochastic Gradient Descent 更多
Over-fitting	过拟合	Erin Kelly 更多	On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation 更多
Regularization	正则化	Stanley Osher 更多	Regularization and variable selection via the elastic net 更多
Cross Validation	交叉验证	Sandrine Dudoit 更多	Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation 更多
Perceptron	感知机	Shun-Ichi Amari 更多	Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms 更多
Logistic Regression	逻辑回归	David W. Hosmer 更多	Applied logistic regression 更多
Maximum Likelihood Estimation	最大似然估计	Mark J. Van Der Laan 更多	MAXIMUM LIKELIHOOD ESTIMATION AND INFERENCE ON COINTEGRATION - WITH APPLICATIONS TO THE DEMAND FOR MONEY 更多
Newton’s method	牛顿法	Liqun Qi(祁力群) 更多	Inexact Newton Methods 更多
K-Nearest Neighbor	K近邻法	Cyrus Shahabi 更多	Fast k Nearest Neighbor Search using GPU 更多
Mahanalobis Distance	马氏距离	Shuran Song 更多	Implementation Hough Method and Mahanalobis Distance In Iris Biometric Identification System 更多
Decision Tree	决策树	Xizhao Wang(王熙照) 更多	Simplifying decision trees 更多
Naive Bayes Classifier	朴素贝叶斯分类器	Geoffrey I. Webb 更多	Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid 更多

机器学习理论

英文	中文	相关学者	相关论文
Generalization Error	泛化误差	MohamedSlim Alouini 更多	Inference for the Generalization Error 更多
PAC Learning	概率近似正确学习	William W. Cohen 更多	PAC Learning from Positive Statistical Queries 更多
Empirical Risk Minimization	经验风险最小化	Rong Ge 更多	Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization 更多
Growth Function	成长函数	Vicent Caselles 更多	One-dimensional ZnO nanostructures: Solution growth and functional properties 更多
VC-dimension	VC维	Marek Karpinski 更多	Measuring the VC-dimension of a learning machine 更多
Structural Risk Minimization	结构风险最小化	John Shawe-Taylor 更多	Structural risk minimization over data-dependent hierarchies 更多
Eigendecomposition	特征分解	Jose C. Principe 更多	Eigenbehaviors: identifying structure in routine 更多

Applied Math

英文	中文	相关学者	相关论文
Singular Value Decomposition	奇异值分解	Bart De Moor 更多	Incremental Singular Value Decomposition of Uncertain Data with Missing Values 更多
Moore-Penrose Pseudoinverse	摩尔－彭若斯广义逆	Eike Kiltz 更多	A note on secure computation of the moore-penrose pseudoinverse and its application to secure linear algebra 更多
Marginal Probability	边缘概率	Marcel Van Herk 更多	Batch Mode Active Sampling based on Marginal Probability Distribution Matching 更多
Conditional Probability	条件概率	Nick Chater 更多	Lexicographic probability, conditional probability, and nonstandard probability 更多
Expectation	期望	Charles F. Manski 更多	Expectation-based syntactic comprehension 更多
Variance	方差	David Goldsman 更多	A new method for non-parametric multivariate analysis of variance 更多
Covariance	协方差	Jianqing Fan(范剑青) 更多	Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift 更多
Critical points	临界点	Subir Sachdev 更多	Deconfined quantum critical points 更多

SVM

英文	中文	相关学者	相关论文
Support Vector Machine	支持向量机	Bernhard Schölkopf 更多	Fast training Support Vector Machines using parallel Sequential Minimal Optimization 更多
Decision Boundary	决策边界	Robert M. Nosofsky 更多	Output-Sensitive Algorithms for Computing Nearest-Neighbour Decision Boundaries 更多
Convex Set	凸集	Vicent Caselles 更多	Learning the Kernel Function via Regularization 更多
Lagrange Duality	拉格朗日对偶性	R. Terry Rockafellar 更多	On strong and total Lagrange duality for convex optimization problems 更多
KKT Conditions	KKT条件	Ying Chen(陈颖) 更多	On the solution of the KKT conditions of generalized Nash equilibrium problems 更多
Coordinate ascent	坐标下降法	Tong Zhang(张潼) 更多	Communication-Efficient Distributed Dual Coordinate Ascent 更多
Sequential Minimal Optimization (SMO)	序列最小化优化	John C. Platt 更多	Fast training Support Vector Machines using parallel Sequential Minimal Optimization 更多

Ensemble

英文	中文	相关学者	相关论文
Ensemble Learning	集成学习	Zhihua Zhou(周志华) 更多	Ensemble Learning 更多
Bootstrap Aggregating (Bagging)	装袋算法	Jie Zhang(张杰) 更多	Double-Bagging: Combining classifiers by bootstrap aggregation 更多
Random Forests	随机森林	Horst Bischof 更多	Conditional variable importance for random forests 更多
Boosting	提升方法	Robert E. Schapire 更多	Robust Real-Time Face Detection 更多
Stacking	堆叠方法	Akira Toriumi 更多	Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion 更多
Decision Tree	决策树	Xizhao Wang(王熙照) 更多	Experiments with a New Boosting Algorithm 更多
Classification Tree	分类树	Taghi M. Khoshgoftaar 更多	Classification Trees With Unbiased Multiway Splits 更多
Adaptive Boosting (AdaBoost)	自适应提升	Jianfeng Gao 更多	Non-Linear Domain Adaptation with Boosting 更多
Decision Stump	决策树桩	Sotiris B. Kotsiantis 更多	Averaging over decision stumps 更多
Meta Learning	元学习	Salvatore J. Stolfo 更多	Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks 更多
Gradient Descent	梯度下降	Zejin Liu(刘泽金) 更多	Reducing the Dimensionality of Data with Neural Networks 更多

DNN

英文	中文	相关学者	相关论文
Deep Feedforward Network (DFN)	深度前向网络	Yoshua Bengio 更多	Understanding the difficulty of training deep feedforward neural networks 更多
Backpropagation	反向传播	Yann LeCun 更多	Backpropagation Applied to Handwritten Zip Code Recognition 更多
Activation Function	激活函数	Jinde Cao(曹进德) 更多	A new learning algorithm for blind source separation 更多
Multi-layer Perceptron (MLP)	多层感知机	Yoshifumi Nishio 更多	Comparison Between Geometry-Based and Gabor-Wavelets-Based Facial Expression Recognition Using Multi-Layer Perceptron 更多
Perceptron	感知机	Shun-Ichi Amari 更多	Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms 更多
Mean-Squared Error (MSE)	均方误差	Yonina Eldar 更多	Mutual information and minimum mean-square error in Gaussian channels 更多
Chain Rule	链式法则	Krzysztof Pietrzak 更多	Geometrical explanation of the fractional complex transform and derivative chain rule for fractional calculus 更多
Logistic Function	逻辑函数	Raymond J. Carroll 更多	Learning Polyhedral Classifiers Using Logistic Function 更多
Hyperbolic Tangent	双曲正切函数	Noreen Sher Akbar 更多	Symbolic computation of hyperbolic tangent solutions for nonlinear differential–difference equations 更多
Rectified Linear Units (ReLU)	整流线性单元	Geoffrey E. Hinton 更多	Rectified Linear Units Improve Restricted Boltzmann Machines 更多
Residual Neural Networks (ResNet)	残差神经网络	Rita Casadio 更多	Aggregated Residual Transformations for Deep Neural Networks 更多

Regularization

英文	中文	相关学者	相关论文
Regularization	正则化	Stanley Osher 更多	Regularization and variable selection via the elastic net 更多
Overfitting	过拟合	Erin Kelly 更多	On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation 更多
Data(set) Augmentation	数据增强	Jun Zhu(朱军) 更多	Learning Deep Sigmoid Belief Networks with Data Augmentation 更多
Parameter Sharing	参数共享	Geert Molenberghs 更多	Efficient Neural Architecture Search via Parameter Sharing 更多
Ensemble Learning	集成学习	Xin Yao(姚新) 更多	Ensembles of Learning Machines 更多
Dropout		Huijun Gao(高会军) 更多	Dropout: a simple way to prevent neural networks from overfitting 更多
L2 Regularization	L2正则化	Andrew Y. Ng(吴恩达) 更多	Fast, Exact Model Selection and Permutation Testing for l2-Regularized Logistic Regression 更多
Taylor Series Approximation	泰勒级数近似	Xihong Lin(林希虹) 更多	Taylor Series Approximations to Expected Utility and Optimal Portfolio Choice 更多
Taylor Expansion	泰勒展开	Maciej Ciesielski 更多	Taylor Expansion Diagrams: A Canonical Representation for Verification of Data Flow Designs 更多
Bayesian Prior	贝叶斯先验	Aggelos K. Katsaggelos 更多	Incorporating Economic Objectives into Bayesian Priors: Portfolio Choice under Parameter Uncertainty 更多
Bayesian Inference	贝叶斯推理	David B. Dunson 更多	MRBAYES: Bayesian inference of phylogenetic trees 更多
Gaussian Prior	高斯先验	Carl Edward Rasmussen 更多	Learning sparse codes with a mixture-of-Gaussians prior 更多
Maximum-a-Posteriori (MAP)	最大后验	Chin-Hui Lee 更多	Person Authentication Using Brainwaves (EEG) and Maximum A Posteriori Model Adaptation 更多
Linear Regression	线性回归	Jean-Marie Dufour 更多	Least angle regression 更多
L1 Regularization	L1正则化	Zongben Xu(徐宗本) 更多	Parallel Coordinate Descent for L1-Regularized Loss Minimization 更多
Constrained Optimization	约束优化	Carlos Artemio Coello Coello 更多	Nonlinear total variation based noise removal algorithms 更多
Lagrange Function	拉格朗日函数	Xiaoqi Yang(杨晓琪) 更多	Recovering Linear Operators and Lagrange Function Minimality Condition 更多
Denoising Autoencoder	降噪自动编码器	Yoshua Bengio 更多	Extracting and composing robust features with denoising autoencoders 更多
Label Smoothing	标签平滑	Konrad Schindler 更多	When Does Label Smoothing Help? 更多
Eigen Decomposition	特征分解	Diannong Liang(梁甸农) 更多	Matrix Eigen-decomposition via Doubly Stochastic Riemannian Optimization 更多
Convolutional Neural Networks (CNNs)	卷积神经网络	U. Rajendra Acharya 更多	ImageNet Classification with Deep Convolutional Neural Networks 更多
Semi-Supervised Learning	半监督学习	Zhihua Zhou(周志华) 更多	Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions 更多
Generative Model	生成模型	David A. Randall 更多	Stochastic Backpropagation and Approximate Inference in Deep Generative Models 更多
Discriminative Model	判别模型	Hermann Ney 更多	Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering 更多
Multi-Task Learning	多任务学习	Jieping Ye(叶杰平) 更多	Facial Landmark Detection by Deep Multi-task Learning 更多
Bootstrap Aggregating (Bagging)	装袋算法	Jie Zhang(张杰) 更多	A reliable multi-objective control strategy for batch processes based on bootstrap aggregated neural network models 更多
Multivariate Normal Distribution	多元正态分布	Rachid Deriche 更多	Clustering Multivariate Normal Distributions 更多
Sparse Parametrization	稀疏参数化	Guillermo Sapiro 更多	Sparse-parametric writer identification using heterogeneous feature groups 更多
Sparse Representation	稀疏表示	Michael Elad 更多	Efficient Learning of Sparse Representations with an Energy-Based Model 更多
Student-t Prior	学生T先验	Aristidis Likas 更多	Student-t Processes as Alternatives to Gaussian Processes 更多
KL Divergence	KL散度	Frank K. Soong(宋謌平) 更多	An Efficient Image Similarity Measure Based on Approximations of KL-Divergence Between Two Gaussian Mixtures 更多
Orthogonal Matching Pursuit (OMP)	正交匹配追踪算法	Anna C. Gilbert 更多	Sparse Solution of Underdetermined Systems of Linear Equations by Stagewise Orthogonal Matching Pursuit 更多
Adversarial Training	对抗训练	John C. Duchi 更多	Domain-Adversarial Training of Neural Networks 更多

Matrix Factorization

英文	中文	相关学者	相关论文
Matrix Factorization (MF)	矩阵分解	Andrzej Cichocki 更多	Algorithms for non-negative matrix factorization 更多
Root-Mean-Square Error (RMSE)	均方根误差	Tianyou Chai(柴天佑) 更多	Mutual information and minimum mean-square error in Gaussian channels 更多
Collaborative Filtering (CF)	协同过滤	Joseph A. Konstan 更多	Item-based collaborative filtering recommendation algorithms 更多
Nonnegative Matrix Factorization (NMF)	非负矩阵分解	Andrzej Cichocki 更多	Overlapping community detection at scale: a nonnegative matrix factorization approach 更多
Singular Value Decomposition (SVD)	奇异值分解	Bart De Moor 更多	Incremental Singular Value Decomposition of Uncertain Data with Missing Values 更多
Latent Sematic Analysis (LSA)	潜在语义分析	Drea Zigarmi 更多	Latent variable models for neural data analysis 更多
Bayesian Probabilistic Matrix Factorization (BPMF)	贝叶斯概率矩阵分解	Ruslan Salakhutdinov 更多	Dynamic Bayesian Probabilistic Matrix Factorization 更多
Wishart Prior	Wishart先验	Shoko Araki 更多	Efficient Gaussian graphical model determination under G-Wishart prior distributions 更多
Sparse Coding	稀疏编码	Andrew Y. Ng(吴恩达) 更多	Efficient sparse coding algorithms 更多
Factorization Machines (FM)	分解机	Lars Schmidt-Thieme 更多	Fast context-aware recommendations with factorization machines 更多

Optimization

英文	中文	相关学者	相关论文
second-order method	二阶方法	Ruqin Yu(俞汝勤) 更多	Pseudo-second order model for sorption processes 更多
cost function	代价函数	Mark V. Pauly 更多	Learning to Rank with Nonsmooth Cost Functions 更多
training set	训练集	Wen Gao(高文) 更多	Addressing the Curse of Imbalanced Training Sets: One-Sided Selection 更多
objective function	目标函数	Kevin W. Bowyer 更多	A Diversity-Promoting Objective Function for Neural Conversation Models 更多
expectation	期望	Charles F. Manski 更多	Expectation-based syntactic comprehension 更多
data generating distribution	数据生成分布	Moni Naor 更多	The generalized distributive law 更多
empirical risk minimization	经验风险最小化	Aaron Sidford 更多	Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds 更多
generalization error	泛化误差	MohamedSlim Alouini 更多	Maximum-Margin Matrix Factorization 更多
empirical risk	经验风险	Georges Dionne 更多	Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization 更多
overfitting	过拟合	David H. Bailey 更多	Dropout: a simple way to prevent neural networks from overfitting 更多
feasible	可行	Ara Darzi 更多	Feasibility of treating prehypertension with an angiotensin-receptor blocker 更多
loss function	损失函数	Chung-Ho Chen 更多	Hypogonadotropic hypogonadism due to loss of function of the KiSS1-derived peptide receptor GPR54 更多
derivative	导数	Dieter Seebach 更多	Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks 更多
gradient descent	梯度下降	Nathan Srebro 更多	Learning to rank using gradient descent 更多
surrogate loss function	代理损失函数	Michael I. Jordan 更多	Divergences, surrogate loss functions and experimental design 更多
early stopping	提前终止	Victor M. Montori 更多	Early Stopping-But When? 更多
Hessian matrix	黑塞矩阵	Christopher M. Bishop 更多	Exact calculation of the Hessian matrix for the multilayer perceptron 更多
second derivative	二阶导数	Zhongmin Su(苏忠民) 更多	Noninvasive method for measuring local hemoglobin oxygen saturation in tissue using wide gap second derivative near-infrared spectroscopy 更多
Taylor series	泰勒级数	Alex Acero 更多	Solving Differential-Algebraic Equations by Taylor Series (I): Computing Taylor Coefficients 更多
Ill-conditioning	病态的	Richard G. Baraniuk 更多	ForWaRD: Fourier-wavelet regularized deconvolution for ill-conditioned systems 更多
critical point	临界点	Subir Sachdev 更多	Deconfined quantum critical points 更多
local minimum	局部极小点	Gregory Dudek 更多	Localized minimum-energy broadcasting in ad-hoc networks 更多
local maximum	局部极大点	Kaile Su(苏开乐) 更多	Binarization of historical document images using the local maximum and minimum 更多
saddle point	鞍点	Michele Benzi 更多	Escaping From Saddle Points - Online Stochastic Gradient for Tensor Decomposition 更多
local minima	局部极小值	Fernando De La Torre 更多	Nonlinear Dimensionality Reduction by Locally Linear Embedding 更多
global minimum	全局最小点	Henry F. Schaefer 更多	Global Minimum for Active Contour Models: A Minimal Path Approach 更多
convex function	凸函数	Khalida Inayat Noor 更多	Image recovery via total variation minimization and related problems 更多
weight space symmetry	权重空间对称性	Per Berglund 更多	Pairing in a two-component ultracold Fermi gas: Phases with broken-space symmetries 更多
Newton’s method	牛顿法	Liqun Qi(祁力群) 更多	Trust region Newton methods for large-scale logistic regression 更多
activation function	激活函数	David A. Boas 更多	Multilayer feedforward networks with a nonpolynomial activation function can approximate any function 更多
fully-connected networks	全连接网络	Shlomo Shamai 更多	DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs 更多
Resnet	残差神经网络	Christian Szegedy 更多	The Shattered Gradients Problem: If resnets are the answer, then what is the question? 更多
gradient clipping	梯度截断	Wolfgang Heidrich 更多	Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity 更多
recurrent neural network	循环神经网络	Yoshua Bengio 更多	http://Speech Recognition with Deep Recurrent Neural Networks 更多
long-term dependency	长期依赖	Eric R. Kandel 更多	Learning long-term dependencies with gradient descent is difficult 更多
eigen-decomposition	特征值分解	Jian Yang(杨坚) 更多	Matrix Eigen-decomposition via Doubly Stochastic Riemannian Optimization 更多
feedforward network	前馈网络	Deshuang Huang(黄德双) 更多	Multilayer feedforward networks are universal approximators 更多
vanishing and exploding gradient problem	梯度消失与爆炸问题	Venkatesh Saligrama 更多	RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients? 更多
contrastive divergence	对比散度	Geoffrey E. Hinton 更多	On the Convergence Properties of Contrastive Divergence 更多
validation set	验证集	Gerold Stucki 更多	Representing shape with a spatial pyramid kernel 更多
stochastic gradient descent	随机梯度下降	Nathan Srebro 更多	Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent 更多
learning rate	学习速率	Michael N. Vrahatis 更多	Multiagent learning using a variable learning rate 更多
momentum	动量	G. Aad 更多	On the importance of initialization and momentum in deep learning 更多
gradient descent	梯度下降	Zejin Liu(刘泽金) 更多	Reducing the Dimensionality of Data with Neural Networks 更多
poor conditioning	病态条件	Ali Ramazani 更多	Only females in poor condition display a clear preference and prefer males with an average badge 更多
nesterov momentum	Nesterov 动量	Xiaohua Hu(胡晓桦) 更多	Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems 更多
partial derivative	偏导数	Avi Wigderson 更多	Combinatorics of Partial Derivatives 更多
moving average	移动平均	Geert Leus 更多	Co-integration and error correction: representation, estimation, and testing 更多
quadratic function	二次函数	Madjid Eshaghi Gordji 更多	On the Generalized Hyers-Ulam-Rassias Stability of Quadratic Functional Equations 更多
positive definite	正定	Liqun Qi(祁力群) 更多	Hermitian and Skew-Hermitian Splitting Methods for Non-Hermitian Positive Definite Linear Systems 更多
quasi-newton method	拟牛顿法	YaXiang Yuan(袁亚湘) 更多	A Stochastic Quasi-Newton Method for Online Convex Optimization 更多
conjugate gradient	共轭梯度	Yuhong Dai(戴彧虹) 更多	An Introduction to the Conjugate Gradient Method Without the Agonizing Pain 更多
steepest descent	最速下降	Jen-Chih Yao(姚任之) 更多	Minimizing the description length using steepest descent 更多
reparametrization	重参数化	Liyong Shen 更多	Reparametrizations of Continuous Paths 更多
standard deviation	标准差	Frederick Mosteller 更多	Interpretation of changes in health-related quality of life: the remarkable universality of half a standard deviation 更多
coordinate descent	坐标下降	Cho-Jui Hsieh(謝卓叡) 更多	An Asynchronous Parallel Stochastic Coordinate Descent Algorithm 更多
skip connection	跳跃连接	Chunhua Shen(沈春华) 更多	Image Super-Resolution Using Dense Skip Connections 更多

CNN

英文	中文	相关学者	相关论文
convolutional neural network	卷积神经网络	U. Rajendra Acharya 更多	ImageNet Classification with Deep Convolutional Neural Networks 更多
convolution	卷积	Yann LeCun 更多	Going Deeper with Convolutions 更多
pooling	池化	Paolo Boffetta 更多	Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition 更多
feedforward neural network	前馈神经网络	Deshuang Huang(黄德双) 更多	Understanding the difficulty of training deep feedforward neural networks 更多
maximum likelihood	最大似然	Ziheng Yang(杨子恒) 更多	MEGA5: molecular evolutionary genetics analysis using maximum likelihood, evolutionary distance, and maximum parsimony methods 更多
back propagation	反向传播	Geoffrey E. Hinton 更多	Learning internal representations by error propagation 更多
artificial neural network	人工神经网络	Sovan Lek 更多	Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks 更多
deep feedforward network	深度前馈网络	Xavier Glorot 更多	Understanding the difficulty of training deep feedforward neural networks 更多
hyperparameter	超参数	Lars Schmidt-Thieme 更多	Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms 更多
sparse connectivity	稀疏连接	Jieping Ye(叶杰平) 更多	ICA with sparse connections 更多
parameter sharing	参数共享	Geert Molenberghs 更多	Efficient Neural Architecture Search via Parameter Sharing 更多
receptive field	接受域	Lars Arendt-Nielsen 更多	Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects 更多
chain rule	链式法则	Gail E. Kaiser 更多	Geometrical explanation of the fractional complex transform and derivative chain rule for fractional calculus 更多
tiled convolution	平铺卷积	Andrew Y. Ng(吴恩达) 更多	Tiled convolutional neural networks 更多
object detection	目标检测	Luc Van Gool 更多	Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 更多
error rate	错误率	MohamedSlim Alouini 更多	Controlling the false discovery rate: a practical and powerful approach to multiple testing 更多
activation function	激活函数	David A. Boas 更多	A new learning algorithm for blind source separation 更多
overfitting	过拟合	C. Lee Giles 更多	Dropout: a simple way to prevent neural networks from overfitting 更多
attention mechanism	注意力机制	John J. Foxe 更多	Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism 更多
transfer learning	迁移学习	Qiang Yang(杨强) 更多	Boosting for transfer learning 更多

Auto Encoder

英文	中文	相关学者	相关论文
autoencoder	自编码器	Björn Schuller 更多	Extracting and composing robust features with denoising autoencoders 更多
unsupervised learning	无监督学习	Andrew Y. Ng(吴恩达) 更多	Building high-level features using large scale unsupervised learning 更多
back propagation	反向传播	Geoffrey E. Hinton 更多	Learning internal representations by error propagation 更多
pretraining	预训练	Ruslan Salakhutdinov 更多	Exploring the Limits of Weakly Supervised Pretraining 更多
dimensionality reduction	降维	Feiping Nie(聂飞平) 更多	Nonlinear Dimensionality Reduction by Locally Linear Embedding 更多
curse of dimensionality	维数灾难	Charu C. Aggarwal 更多	On k-anonymity and the curse of dimensionality 更多
feedforward neural network	前馈神经网络	Deshuang Huang(黄德双) 更多	Understanding the difficulty of training deep feedforward neural networks 更多
encoder	编码器	Bahram Javidi 更多	Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation 更多
decoder	解码器	Lajos Hanzo 更多	Decoding by linear programming 更多
cross-entropy	交叉熵	Yiquan Wu(吴一全) 更多	A tutorial on the cross-entropy method 更多
tied weights	绑定的权重	Tao Zhou(周涛) 更多	Pelvic adenopathy in prostatic and urinary bladder carcinoma: MR imaging with a three-dimensional TI-weighted magnetization-prepared-rapid gradient-echo sequence 更多
PCA	PCA	Jingyu Yang(杨静宇) 更多	PCA-SIFT: a more distinctive representation for local image descriptors 更多
principal component analysis	主成分分析	Yi Ma(马毅) 更多	Principal component analysis 更多
singular value decomposition	奇异值分解	Bart De Moor 更多	Incremental Singular Value Decomposition of Uncertain Data with Missing Values 更多
SVD	SVD	Michael Elad 更多	Learning Topic Models -- Going beyond SVD 更多
singular value	奇异值	Ravi P. Agarwal 更多	A Singular Value Thresholding Algorithm for Matrix Completion 更多
reconstruction error	重构误差	Raghu Machiraju 更多	Generalized low rank approximations of matrices 更多
covariance matrix	协方差矩阵	Jianqing Fan(范剑青) 更多	Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES) 更多
Kullback-Leibler (KL) divergence	KL散度	Biao Huang(黄彪) 更多	Constrained Extended Kalman Filter based on Kullback-Leibler (KL) Divergence 更多
denoising autoencoder	去噪自编码器	Pascal Vincent 更多	Extracting and composing robust features with denoising autoencoders 更多
sparse autoencoder	稀疏自编码器	Anant Madabhushi 更多	k-Sparse Autoencoders 更多
contractive autoencoder	收缩自编码器	James She(許丕文) 更多	Multimodal video classification with stacked contractive autoencoders 更多
conjugate gradient	共轭梯度	Yuhong Dai(戴彧虹) 更多	GMRES: a generalized minimal residual algorithm for solving nonsymmetric linear systems 更多
fine-tune	精调	Howard Baer 更多	Joint Fine-Tuning in Deep Neural Networks for Facial Expression Recognition 更多
local optima	局部最优	Franz Rothlauf 更多	Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima 更多
posterior distribution	后验分布	Qi-Man Shao(邵啟滿) 更多	The calculation of posterior distributions by data augmentation 更多
gaussian distribution	高斯分布	Philippe Grangier 更多	Adaptive Background Mixture Models for Real-Time Tracking 更多
reparametrization	重参数化	William L. Jorgensen 更多	Reparametrizations of Continuous Paths 更多

RNN

英文	中文	相关学者	相关论文
recurrent neural network	循环神经网络	Jun Wang(王鈞) 更多	Recurrent neural network based language model 更多
artificial neural network	人工神经网络	Saro Lee 更多	Artificial Neural Network Modeling of the Rainfall-Runoff Process 更多
feedforward neural network	前馈神经网络	Deshuang Huang(黄德双) 更多	Optimal unsupervised learning in a single-layer linear feedforward neural network 更多
sentiment analysis	情感分析	Bing Liu(刘兵) 更多	Opinion Mining and Sentiment Analysis 更多
machine translation	机器翻译	Hermann Ney 更多	Neural Machine Translation by Jointly Learning to Align and Translate 更多
pos tagging	词性标注	Ting Liu(刘挺) 更多	Deep Learning for Chinese Word Segmentation and POS Tagging 更多
teacher forcing	导师驱动过程	Hsiao-Chun Wu 更多	Dream, Design, Deliver: How Singapore Developed a High-Quality Teacher Force 更多
back-propagation through time	通过时间反向传播	Songchun Zhu(朱松纯) 更多	Learning Dynamic Generator Model by Alternating Back-Propagation Through Time 更多
directed graphical model	有向图模型	Mark Schmidt 更多	Model selection and estimation in the Gaussian graphical model 更多
speech recognition	语音识别	Chin-Hui Lee 更多	Speech Recognition with Deep Recurrent Neural Networks 更多
question answering	问答系统	Jimmy Lin 更多	VQA: Visual Question Answering 更多
attention mechanism	注意力机制	Kyunghyun Cho 更多	Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism 更多
vanishing and exploding gradient problem	梯度消失与爆炸问题	Zhouping Xin 更多	RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients? 更多
jacobi matrix	jacobi矩阵	Dumitru Baleanu 更多	Estimates of Parameters for Conformal Mappings Related to a Periodic Jacobi Matrix 更多
long-term dependency	长期依赖	David A. Wardle 更多	Learning long-term dependencies with gradient descent is difficult 更多
clip gradient	梯度截断	Liu Mingyan 更多
long short-term memory	长短期记忆	Björn Schuller 更多	Long short-term memory 更多
gated recurrent unit	门控循环单元	Yan Li(李彦) 更多	QUESTION DETECTION FROM ACOUSTIC FEATURES USING RECURRENT NEURAL NETWORK WITH GATED RECURRENT UNIT 更多
hadamard product	Hadamard乘积	Roger A. Horn 更多	Hadamard Product for Low-rank Bilinear Pooling 更多
back propagation	反向传播	Yann LeCun 更多	Learning internal representations by error propagation 更多
attention mechanism	注意力机制	Yoshua Bengio 更多	Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism 更多
feedforward network	前馈网络	Jiang Wang(王江) 更多	Multilayer feedforward networks are universal approximators 更多
named entity recognition	命名实体识别	Christopher D. Manning 更多	Neural Architectures for Named Entity Recognition 更多

Representation

英文	中文	相关学者	相关论文
Representation Learning	表征学习	Shuicheng Yan(颜水成) 更多	Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks 更多
Distributed Representation	分布式表征	Ruzena Bajcsy 更多	Distributed Representations of Words and Phrases and their Compositionality 更多
Multi-task Learning	多任务学习	Jieping Ye(叶杰平) 更多	A Multi-task Learning Framework for Gas Detection and Concentration Estimation 更多
Multi-Modal Learning	多模态学习	Dacheng Tao(陶大程) 更多	Graph based multi-modality learning 更多
Semi-supervised Learning	半监督学习	Zhi-Hua Zhou(周志华) 更多	Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions 更多
NLP	自然语言处理	Hal Daumé III 更多	A framework and graphical development environment for robust NLP tools and applications 更多
Neural Language Model	神经语言模型	Yoshua Bengio 更多	A neural probabilistic language model 更多
Neural Probabilistic Language Model	神经概率语言模型	Yoshua Bengio 更多	A neural probabilistic language model 更多
RNN	循环神经网络	Zhiheng Huang 更多	Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation 更多
Neural Tensor Network	神经张量网络	Nakamura, Satoshi 更多	Convolutional Neural Tensor Network Architecture for Community-Based Question Answering 更多
Graph Neural Network	图神经网络	Erol Gelenbe 更多	The graph neural network model 更多
Graph Covolutional Network (GCN)	图卷积网络		Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN) 更多
Graph Attention Network	图注意力网络	Jia Li(李佳) 更多	Heterogeneous Graph Attention Network 更多
Self-attention	自注意力机制	Charles S. Carver 更多	A Structured Self-attentive Sentence Embedding 更多
Feature Learning	表征学习	Yann LeCun 更多	node2vec: Scalable Feature Learning for Networks 更多
Feature Engineering	特征工程	Alessandro Moschitti 更多	Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription 更多
One-hot Representation	独热编码	Declercq, D. 更多
Speech Recognition	语音识别	Hermann Ney 更多	Speech Recognition with Deep Recurrent Neural Networks 更多
DBM	深度玻尔兹曼机	Qijin Zhang(张其锦) 更多	Model checking timed automata with priorities using DBM subtraction 更多
Zero-shot Learning	零次学习	Tao Xiang 更多	Zero-shot Learning with Semantic Output Codes 更多
Autoencoder	自编码器	Lawrence Carin 更多	Cross-modal Retrieval with Correspondence Autoencoder 更多
Generative Adversarial Network（GAN）	生成对抗网络	Mubarak Shah 更多	Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network 更多
Approximate Inference	近似推断	Michael I. Jordan 更多	Stochastic Backpropagation and Approximate Inference in Deep Generative Models 更多
Bag-of-Words Model	词袋模型	Zhi-Hua Zhou(周志华) 更多	Understanding bag-of-words model: a statistical framework 更多
Forward Propagation	前向传播	Christophe Bourlier 更多	Gradient calculations for dynamic recurrent neural networks: a survey 更多
Huffman Binary Tree	霍夫曼二叉树	Hyeran Kim 更多	A new binary tree algorithm implementation with Huffman decoder on FPGA 更多
NNLM	神经网络语言模型	Jia Liu(刘加) 更多	Efficient One-Pass Decoding with NNLM for Speech Recognition 更多
N-gram	N元语法	Fuchun Peng 更多	Class-based n-gram models of natural language 更多
Skip-gram Model	跳元模型	Xuanjing Huang(黄萱菁) 更多	A Closer Look at Skip-gram Modelling 更多
Negative Sampling	负采样	Alistair Sinclair 更多	Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling 更多
CBOW	连续词袋模型	Maarten De Rijke 更多	Siamese CBOW: Optimizing Word Embeddings for Sentence Representations 更多
Knowledge Graph	知识图谱	Xiaoyan Zhu(朱小燕) 更多	Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction 更多
Relation Extraction	关系抽取	Raymond J. Mooney 更多	Distant supervision for relation extraction without labeled data 更多

Network Embedding

英文	中文	相关学者	相关论文
Node Embedding	节点嵌入	Kevin Chen-Chuan Chang 更多	Learning Structural Node Embeddings via Diffusion Wavelets 更多
Graph Neural Network	图神经网络	Ah Chung Tsoi(蔡亞從) 更多	Simplifying Graph Convolutional Networks 更多
Node Classification	节点分类	Node Classification 更多	Active learning for node classification in assortative and disassortative networks 更多
Link Prediction	链路预测	Nitesh V. Chawla 更多	The link prediction problem for social networks 更多
Community Detection	社区发现	Licheng Jiao(焦李成) 更多	Resolution limit in community detection 更多
Isomorphism	同构	Gary L. Miller 更多	The Iron Cage Revisited: Institutional Isomorphism and Collective Rationality in Organizational Fields 更多
Random Walk	随机漫步	George H. Weiss 更多	Distribution of the Estimators for Autoregressive Time Series with a Unit Root 更多
Spectral Clustering	谱聚类	Johan Suykens 更多	On Spectral Clustering: Analysis and an algorithm 更多
Asynchronous Stochastic Gradient Algorithm	异步随机梯度算法	Risheng Liu(刘日升) 更多	Asynchronous Proximal Stochastic Gradient Algorithm for Composition Optimization Problems 更多
Negative Sampling	负采样	Weinan Zhang(张伟楠) 更多	word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method 更多
Network Embedding	网络嵌入	Raouf Boutaba 更多	LINE: Large-scale Information Network Embedding 更多
Graph Theory	图论	A. Kaveh 更多	Algorithmic graph theory and perfect graphs 更多
multiset	多重集	Toby Walsh 更多	Genetic Set Recombination and Its Application to Neural Network Topology Optimisation 更多
Perron-Frobenius Theorem	佩龙—弗罗贝尼乌斯定理	Qingzhi Yang(杨庆之) 更多	The Perron-Frobenius Theorem for Homogeneous, Monotone Functions 更多
Stationary Distribution	稳态分布	Qun Liu(刘群) 更多	Stationary Distributions for the Random Waypoint Mobility Model 更多
Matrix Factorization	矩阵分解	Andrzej Cichocki 更多	Algorithms for non-negative matrix factorization 更多
Sparsification	稀疏化	Daniel A. Spielman 更多	Quantized kernel recursive least squares algorithm 更多
Singular Value Decomposition	奇异值分解	Bart De Moor 更多	Lingo: Search Results Clustering Algorithm Based on Singular Value Decomposition 更多
Frobenius Norm	F-范数	W. M. Haddad 更多	Incorporating minimum Frobenius norm models in direct search 更多
Heterogeneous Network	异构网络	Philip S. Yu 更多	metapath2vec: Scalable Representation Learning for Heterogeneous Networks 更多
Graph Convolutional Network （GCN）	图卷积网络	Jiliang Tang 更多	Signed Graph Convolutional Network 更多
CNN	卷积神经网络	Leon O.Chua 更多	Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks 更多
Semi-Supervised Classification	半监督分类	Changshui Zhang(张长水) 更多	Semi-Supervised Classification with Graph Convolutional Networks 更多
Chebyshev polynomial	切比雪夫多项式	John P. Boyd 更多	Restricted even permutations and Chebyshev polynomials 更多
Gradient Exploding	梯度爆炸	Yoshua Bengio 更多	Gradients explode - Deep Networks are shallow - ResNet explained 更多
Gradient Vanishing	梯度消失	Sepp Hochreiter 更多	Inception Score, Label Smoothing, Gradient Vanishing and -log(D(x)) Alternative 更多
Batch Normalization	批标准化	Aleksander Madry 更多	Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift 更多
Neighborhood Aggregation	邻域聚合	Liang-Tien Chia 更多	Internet bad neighborhoods aggregation 更多
LSTM	长短期记忆网络	Jürgen Schmidhuber 更多	Mogrifier LSTM 更多
Graph Attention Network	图注意力网络	Hui Xiong(熊辉) 更多	Graph Attention Networks 更多
Self-attention	自注意力机制	Charles S. Carver 更多	A Structured Self-attentive Sentence Embedding 更多
Rescaling	再缩放	Mark D. Fairchild 更多	The limits to scale? Methodological reflections on scalar structuration 更多
Attention Mechanism	注意力机制	Kyunghyun Cho 更多	Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism 更多
Jensen-Shannon Divergence	JS散度	Edwin R. Hancock 更多	Metric character of the quantum Jensen-Shannon divergence 更多
Cognitive Graph	认知图谱	Seok-Hee Hong 更多	Learn to Explain Efficiently via Neural Logic Inductive Learning 更多

GAN

英文	中文	相关学者	相关论文
Generative Adversarial Network(GAN)	生成对抗网络	Brian C. Lovell 更多	Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks 更多
Generative Model	生成模型	Alex Graves 更多	Stochastic Backpropagation and Approximate Inference in Deep Generative Models 更多
Discriminative Model	判别模型	Greg Mori 更多	Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering 更多
Gaussian Mixture Model	高斯混合模型	Tomoki Toda 更多	Improved Adaptive Gaussian Mixture Model for Background Subtraction 更多
Variational Auto-Encoder（VAE）	变分编码器	Max Welling 更多	Denoising Criterion for Variational Auto-Encoding Framework 更多
Markov Chain	马尔可夫链	Arnaud Doucet 更多	Reversible jump Markov chain Monte Carlo computation and Bayesian model determination 更多
Boltzmann Machine	玻尔兹曼机	Geoffrey E. Hinton 更多	Rectified Linear Units Improve Restricted Boltzmann Machines 更多
Kullback–Leibler divergence	KL散度	John R. Hershey 更多	A Kullback-Leibler Divergence Based Kernel for SVM Classification in Multimedia Applications 更多
Vanishing Gradient	梯度消失	Sepp Hochreiter 更多	Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients? 更多
Surrogate Loss	替代损失	Michael I. Jordan 更多	On the (Non-)existence of Convex, Calibrated Surrogate Losses for Ranking 更多
Mode Collapse	模式崩溃	Butrus Khuri-Yakub 更多	VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning 更多
Earth-Mover/Wasserstein-1 Distance	搬土距离/EMD	Piotr Indyk 更多	The Earth Mover's Distance as a Metric for Image Retrieval 更多
Lipschitz Continuity	利普希茨连续	Le Yi Wang 更多	Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization 更多
Feedforward Network	前馈网络	Deshuang Huang(黄德双) 更多	Multilayer feedforward networks with a nonpolynomial activation function can approximate any function 更多
Minimax Game	极小极大博弈	Judea Pearl 更多	IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models 更多

Adversarial Learning

英文	中文	相关学者	相关论文
Adversarial Learning	对抗学习	Patrick Drew McDaniel(帕特里克·德鲁·麦克丹尼尔) 更多	Semantic Adversarial Deep Learning 更多
Outlier	异常值/离群值	Charu C. Aggarwal 更多	LOCI: Fast Outlier Detection Using the Local Correlation Integral 更多
Rectified Linear Unit	线性修正单元	Hong Cheng(程洪) 更多	Rectified Linear Units Improve Restricted Boltzmann Machines 更多
Logistic Regression	逻辑回归	Biswajeet Pradhan 更多	On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes 更多
Softmax Regression	Softmax回归	Yu Xue(薛宇) 更多	Text classification based on deep belief network and softmax regression 更多
SVM	支持向量机	Thorsten Joachims 更多	On the Learnability and Design of Output Codes for Multiclass Problems 更多
Decision Tree	决策树	Louis Wehenkel 更多	Simplifying decision trees 更多
Nearest Neighbors	最近邻	Piotr Indyk 更多	When Is ''Nearest Neighbor'' Meaningful? 更多
White-box	白盒（测试 etc. ）	Bart Preneel 更多	A White-Box DES Implementation for DRM Applications 更多
Lagrange Multiplier	拉格朗日乘子	Roland Glowinski 更多	Lagrange multiplier selection in hybrid video coder control 更多
Black-box	黑盒（测试 etc. ）	Lennart Ljung 更多	Efficient Global Optimization of Expensive Black-Box Functions 更多
Robustness	鲁棒性/稳健性	Shlomo Havlin 更多	ImageNet: A large-scale hierarchical image database 更多
Decision Boundary	决策边界	David A. Landgrebe 更多	Output-Sensitive Algorithms for Computing Nearest-Neighbour Decision Boundaries 更多
Non-differentiability	不可微	Yimin Xiao(肖益民) 更多	About Non-differentiable Functions 更多
Intra-technique Transferability	相同技术迁移能力		Adversarial Perturbation Intensity Achieving Chosen Intra-Technique Transferability Level for Logistic Regression 更多
Cross-technique Transferability	不同技术迁移能力
Data Augmentation	数据增强	Jun Zhu(朱军) 更多	Learning Deep Sigmoid Belief Networks with Data Augmentation 更多

Online Learning

英文	中文	相关学者	相关论文
Adaboost		Robert E. Schapire 更多	Robust object detection using a boosted cascade of simple features 更多
recommender system	推荐系统	John T. Riedl 更多	Evaluating collaborative filtering recommender systems 更多
Probability matching	概率匹配	Fred W. Mclafferty 更多	On probability matching priors 更多
minimax regret		Craig Boutilier 更多	Minimax Regret Bounds for Reinforcement Learning 更多
face detection	人脸检测	Wen Gao(高文) 更多	Robust Real-Time Face Detection 更多
i.i.d.	独立同分布	Thomas G. Dietterich 更多	Lifelong Learning with Non-i.i.d. Tasks 更多
Minimax	极大极小	Yonina Eldar 更多	The Adaptive Lasso and Its Oracle Properties 更多
linear model	线性模型	Manfred Morari 更多	Generalized linear models 更多
Thompson Sampling	汤普森抽样	Benjamin Van Roy 更多	Analysis of Thompson Sampling for the multi-armed bandit problem 更多
eigenvalues	特征值	Liqun Qi(祁力群) 更多	ARPACK Users' Guide: Solution of Large Scale Eigenvalue Problems with Implicitly Restarted Arnoldi Methods 更多
optimization problem	优化问题	Yannis Marinakis 更多	Teaching-learning-based optimization: A novel method for constrained mechanical design optimization problems 更多
greedy algorithm	贪心算法	Tong Zhang(张潼) 更多	The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information 更多

Reinforcement Learning

英文	中文	相关学者	相关论文
Dynamic Programming	动态规划	Sergey Levine 更多	Emergent Tool Use From Multi-Agent Autocurricula 更多
lookup table	查找表	Jingsheng Jason Cong(丛京生) 更多	The Bloomier filter: an efficient data structure for static support lookup tables 更多
Bellman equation	贝尔曼方程	Randal Beard 更多	The Uncertainty Bellman Equation and Exploration 更多
discount factor	折现系数	Lars Peter Hansen 更多	The Feeble Link between Exchange Rates and Fundamentals: Can We Blame the Discount Factor? 更多
Reinforcement Learning	强化学习	Peter Stone 更多	Emergent Tool Use From Multi-Agent Autocurricula 更多
gradient theorem	梯度定理	DingZhu Du(堵丁柱) 更多	An Off-policy Policy Gradient Theorem Using Emphatic Weightings 更多
stochastic gradient descent	随机梯度下降法	Zejin Liu(刘泽金) 更多	Large-Scale Machine Learning with Stochastic Gradient Descent 更多
Monte Carlo	蒙特卡罗方法	Arnaud Doucet 更多	Monte Carlo Statistical Methods 更多
function approximation	函数逼近	Richard S. Sutton 更多	Policy Gradient Methods for Reinforcement Learning with Function Approximation 更多
Markov Decision Process	马尔可夫决策过程	Vikram Krishnamurthy 更多	The Infinite Partially Observable Markov Decision Process 更多
Bootstrapping	引导	Ellen Riloff 更多	(Leveled) Fully Homomorphic Encryption without Bootstrapping 更多
Shortest Path Problem	最短路径问题	Mitsuo Gen 更多	An incremental algorithm for a generalization of the shortest-path problem 更多
expected return	预期回报	Robert C. Merton 更多	Maxing out: Stocks as lotteries and the cross-section of expected returns 更多
Q-Learning	Q学习	Frank L. Lewis 更多	Deep Reinforcement Learning with Double Q-learning 更多
temporal-difference learning	时间差分学习	Richard S. Sutton 更多	Practical Issues in Temporal Difference Learning 更多
AlphaZero		Ivan Bratko 更多	ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero 更多
Backgammon	西洋双陆棋	Jordan B. Pollack 更多	Practical Issues in Temporal Difference Learning 更多
finite set	有限集	Ba-Ngu Vo 更多	Optimal Sampling Laws for Stochastically Constrained Simulation Optimization on Finite Sets 更多
Markov property	马尔可夫性质	Alistair Sinclair 更多	An alternative Markov property for chain graphs 更多
sample complexity	样本复杂性	Michael J. Kearns 更多	Reducing the sampling complexity of topic models 更多

AutoML

英文

中文

相关学者

相关论文

Cartesian product

笛卡儿积

Chin-Chen Chang 更多

On the Metric Dimension of Cartesian Products of Graphs 更多

Kevin Leyton-Brown

Kevin Leyton-Brown 更多

Sequential model-based optimization for general algorithm configuration 更多

SVM

支持向量机

Thorsten Joachims 更多

A Structural {SVM} Based Approach for Optimizing Partial AUC 更多

MNIST

ImageNet

Feifei Li (李飞飞) 更多

ImageNet Classification with Deep Convolutional Neural Networks 更多

Ensemble learning

集成学习

Shouyang Wang(汪寿阳) 更多

Ensemble learning 更多

Neural networks

神经网络

Jinde Cao(曹进德) 更多

Efficient Image Retrieval through Hybrid Feature Set and Neural Network 更多

Neuroevolution

神经演化

Risto Miikkulainen 更多

Abandoning objectives: evolution through the search for novelty alone 更多

object recognition

目标识别

Martial H. Hebert 更多

Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression 更多

Multi-task learning

多任务学习

Jieping Ye(叶杰平) 更多

A Multi-task Learning Framework for Gas Detection and Concentration Estimation 更多

Treebank

树图资料库

Martha Palmer 更多

Deep Syntax Annotation of the Sequoia French Treebank 更多

covariance

协方差

Jianqing Fan(范剑青) 更多

Population structure and eigenanalysis 更多

Hamiltonian Monte Carlo

哈密顿蒙特卡罗

Mark A. Girolami 更多

Stochastic Gradient Hamiltonian Monte Carlo 更多

Inductive bias

归纳偏置

Rich Caruana 更多

A model of inductive bias learning 更多

bilevel optimization

双层规划

Kalyanmoy Deb 更多

Multiobjective bilevel optimization 更多

genetic algorithms

遗传算法

David E. Goldberg 更多

Genetic Algorithms and Machine Learning 更多

Bayesian linear regression

贝叶斯线性回归

Adrian E. Raftery 更多

Differentially Private Bayesian Linear Regression 更多

方差分析

外推法

激活函数

Minibatch Approximate Greatest Descent on CIFAR-10 Dataset 更多

Gaussian Process

高斯过程

Carl Edward Rasmussen 更多

Gaussian processes for machine learning 更多

k-nearest neighbors

K最近邻

Xuemin Lin(林学民) 更多

Fast k Nearest Neighbor Search using GPU 更多

Neural Turing machine

神经图灵机

Yoshua Bengio 更多

Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes 更多

MCMC

马尔可夫链蒙特卡罗

Arnaud Doucet 更多

Being Bayesian About Network Structure. A Bayesian Approach to Structure Discovery in Bayesian Networks 更多

Collaborative filtering

协同过滤

John T. Riedl 更多

An algorithmic framework for performing collaborative filtering 更多

AlphaGo

Feiyue Wang(王飞跃) 更多

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks 更多

random forests

随机森林

Horst Bischof 更多

Conditional variable importance for random forests 更多

multivariate Gaussian

多元高斯

Wayne Luk(陆永青) 更多

Differential Entropic Clustering of Multivariate Gaussians 更多

Bayesian Optimization

贝叶斯优化

David E. Goldberg 更多

Practical Bayesian Optimization of Machine Learning Algorithms 更多

meta-learning

元学习

Salvatore J. Stolfo 更多

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks 更多

iterative algorithm

迭代算法

Aggelos K. Katsaggelos 更多

Multi-Task Feature Learning 更多

Graphic Model

英文	中文	相关学者	相关论文
Viterbi algorithm	维特比算法	Jaejin Lee 更多	The viterbi algorithm 更多
Gibbs distribution	吉布斯分布	V. V. Kozlov 更多	Gibbs versus non-Gibbs distributions in money dynamics 更多
Discriminative model	判别模型	Daniel P. W. Ellis 更多	Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering 更多
Maximum Entropy Markov Model	最大熵马尔可夫模型	Bingquan Liu(刘秉权) 更多	Exploiting Pinyin Constraints in Pinyin-to-Character Conversion Task: a Class-Based Maximum Entropy Markov Model Approach 更多
Information Extraction	信息提取	Oren Etzioni 更多	Attention-over-Attention Neural Networks for Reading Comprehension 更多
clique	小圈子	Marcello Pelillo 更多	A random graph model for massive graphs 更多
conditional random field	条件随机场	Liangpei Zhang(张良培) 更多	A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005 更多
CRF	条件随机场	Wylie Vale 更多	The role of corticotropin-releasing factor--norepinephrine systems in mediating the effects of early experience on the development of behavioral and endocrine responses to stress 更多
triad	三元关系	Devens Gust 更多	Novel symmetrical triads of triphenylene-calix[4]arene-triphenylene: Synthesis and mesomorphism 更多
Naïve Bayes	朴素贝叶斯	Geoffrey I. Webb 更多	A comparison of event models for Naive Bayes text classification 更多
social network	社交网络	Jie Tang(唐杰) 更多	Data mining: concepts and techniques 更多
Bayesian network	贝叶斯网络	Sung-Bae Cho 更多	PrivBayes: private data release via bayesian networks 更多
SVM	支持向量机	Thorsten Joachims 更多	On the Learnability and Design of Output Codes for Multiclass Problems 更多
Joint probability distribution	联合概率分布	M. San Miguel 更多	Joint Probability Distribution of Prediction Errors of ARIMA 更多
Conditional independence	条件独立性	Dirk Van Gucht 更多	Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid 更多
sequence analysis	序列分析	Sean R. Eddy 更多	A Scoring Function for Learning Bayesian Networks based on Mutual Information and Conditional Independence Tests 更多
Perceptron	感知器	Michael Collins 更多	Analysis of Perceptron-Based Active Learning 更多
Markov Blanket	马尔科夫毯	Alexander Statnikov 更多	Time and sample efficient discovery of Markov blankets and direct causal relations 更多
Hidden Markov Model	隐马尔可夫模型	Chin-Hui Lee 更多	A Hidden Markov Model for Predicting Transmembrane Helices in Protein Sequences 更多
finite-state	有限状态	Mehryar Mohri 更多	Patterns in property specifications for finite-state verification 更多
Shallow parsing	浅层分析	Walter Daelemans 更多	Shallow parsing with conditional random fields 更多
Active learning	主动学习	Jaime G. Carbonell 更多	Learning Loss for Active Learning 更多
Speech recognition	语音识别	Hermann Ney 更多	State-of-the-art Speech Recognition With Sequence-to-Sequence Models 更多
convex	凸	R. Terry Rockafellar 更多	Advances in Convex Optimization: Conic Programming 更多
transition matrix	转移矩阵	Rudolph A. Marcus(马库斯) 更多	Empirical Transition Matrix of Multi-State Models: The etm Package 更多
factor graph	因子图	Pascal Olivier.VONTOBEL 更多	Factor graphs and the sum-product algorithm 更多
forward-backward algorithm	前向后向算法	Tong Zhang(张潼) 更多	Inside-Outside and Forward-Backward Algorithms Are Just Backprop (tutorial paper) 更多
parsing	语法分析	Christopher D. Manning 更多	From News to Comment: Resources and Benchmarks for Parsing the Language of Web 2.0 更多
structural holes	结构洞	Ronald S. Burt 更多	Social Capital, Structural Holes and the Formation of an Industry Network 更多
graphical model	图模型	Martin J. Wainwright 更多	Probabilistic Graphical Models: Principles and Techniques 更多
Markov Random Field	马尔可夫随机场	Josiane Zerubia 更多	Markov random field models in computer vision 更多
Social balance theory	社会平衡理论	Xuyun Zhang 更多	Some dynamics of social balance processes: bringing Heider back into balance theory 更多
Generative model	生成模型	Alex Graves 更多	Stochastic Backpropagation and Approximate Inference in Deep Generative Models 更多

Topic Model

英文	中文	相关学者	相关论文
probalistic topic model	概率语义模型	David M. Blei 更多	The author-topic model for authors and documents 更多
TFIDF	词频-文本逆向频率	Thorsten Joachims 更多	A Chinese Keywords Extraction Approach Based on TFIDF and Word Correlation 更多
LSI	潜在语义索引	Susan Dumais 更多	Review of laser speckle contrast techniques for visualizing tissue perfusion 更多
Bayesian network	贝叶斯网络模型	Qiang Ji 更多	PrivBayes: private data release via bayesian networks 更多
Markov random field	马尔科夫随机场	Josiane Zerubia 更多	Markov random field models in computer vision 更多
restricted boltzmann machine	限制玻尔兹曼机	Geoffrey E. Hinton 更多	The Recurrent Temporal Restricted Boltzmann Machine 更多
LDA	隐式狄利克雷分配模型	Jingyu Yang(杨静宇) 更多	Random Sampling for Subspace Face Recognition 更多
PLSI	概率潜在语义索引模型	Mark A. Girolami 更多	Google news personalization: scalable online collaborative filtering
EM algorithm	最大期望算法	Edwin R. Hancock 更多	A view of the EM algorithm that justifies incremental, sparse, and other variants 更多
Gibbs sampling	吉布斯采样法	Bart De Moor 更多	Incorporating non-local information into information extraction systems by Gibbs sampling 更多
MAP (Maximum A Posteriori)	最大后验概率算法	Guido Montorsi 更多	A Soft-Input Soft-Output Maximum A Posteriori (MAP) Module to Decode Parallel and Serial Concatenated Codes 更多

MCMC

英文	中文	相关学者	相关论文
Markov Chain Monte Carlo	马尔科夫链式蒙特卡洛算法	Arnaud Doucet 更多	First-row hydrides: Dissociation and ground state energies using quantum Monte Carlo 更多
Monte Carlo Sampling	蒙特卡洛采样法	Daan Frenkel 更多	Generalized likelihood uncertainty estimation (GLUE) using adaptive Markov Chain Monte Carlo sampling 更多
Univariate	单变量	Shu-Cherng Fang(方述誠) 更多	Cellulose I crystallinity determination using FT–Raman spectroscopy: univariate and multivariate methods 更多
Hoeffding Bound	Hoeffding界	Qinbao Song(宋擒豹) 更多	Chernoff-Hoeffding Bounds for Applications with Limited Independence 更多
Chernoff Bound	Chernoff界	Martin E. Hellman 更多	A Chernoff bound for random walks on expander graphs 更多
Importance Sampling	加权采样法	Perwez Shahabuddin 更多	Importance Sampling for Portfolio Credit Risk 更多
invariant distribution	不动点分布	D. Amidei 更多	Information invariants for distributed manipulation 更多
Metropolis-Hastings algorithm	Metropolis-Hastings算法	Persi Diaconis 更多	Understanding the Metropolis-Hastings Algorithm 更多

Mean-Field

英文	中文	相关学者	相关论文
Probablistic Inference	概率推断	Fan Yang(杨帆) 更多	Intrusion Intention Recognition Method Based on Dynamic Bayesian Networks 更多
Variational Inference	变量式推断	David M. Blei 更多	Graphical Models, Exponential Families, and Variational Inference 更多
HMM	隐式马尔科夫模型	Keiichi Tokuda 更多	Non-Intrusive Load Monitoring Using Prior Models of General Appliance Types 更多
mean field	平均场理论	G. Kotliar 更多	Mean field games 更多
mixture model	混合模型	Tomoki Toda 更多	Adaptive Background Mixture Models for Real-Time Tracking 更多
convex duality	凸对偶	R. Terry Rockafellar 更多	Convexity, Duality and Effects 更多
belief propagation	置信传播算法

non-parametric models

英文	中文	相关学者	相关论文
non-parametric model	非参模型	Ahmed Elgammal 更多	Non-parametric Modeling of Partially Ranked Data 更多
Gaussian process	正态过程	Zoubin Ghahramani 更多	Gaussian processes for machine learning 更多
multivariate Gaussian distribution	多元正态分布	Yutian Chen(陈御天) 更多	Sampling from the Multivariate Gaussian Distribution using Reconfigurable Hardware 更多
Dirichlet process	狄利克雷过程	Michael I. Jordan 更多	Hierarchical Dirichlet Processes 更多
stick breaking process	断棒过程	Lawrence Carin 更多	Logistic Stick-Breaking Process 更多
Chinese restaurant process	中餐馆过程	Thomas L. Griffiths 更多	Hierarchical Topic Models and the Nested Chinese Restaurant Process 更多
Blackwell-MacQueen Urn Scheme	Blackwell-MacQueen桶法	Stephen G. Walker 更多	Some Developments of the Blackwell-MacQueen Urn Scheme 更多
De Finetti's theorem	de Finetti定理	Persi Diaconis 更多	A Thinning Analogue of de Finetti's Theorem 更多
collapsed Gibbs sampling	下陷吉布斯采样法	Lior Pachter 更多	Fast collapsed gibbs sampling for latent dirichlet allocation 更多
Hierarchical Dirichlet process	阶梯式狄利克雷过程	Eric P. Xing 更多	Online Variational Inference for the Hierarchical Dirichlet Process 更多
Indian Buffet process	印度餐馆过程	Zoubin Ghahramani 更多	Infinite latent feature models and the Indian buffet process 更多