请选择 进入手机版 | 继续访问电脑版
楼主: CDA网校
16125 56

历史最全机器学习/深度学习/人工智能专业术语表中英对照表   [推广有奖]

  • 3关注
  • 56粉丝

管理员

学术权威

23%

还不是VIP/贵宾

-

威望
3
论坛币
159807 个
通用积分
444.7863
学术水平
143 点
热心指数
153 点
信用等级
132 点
经验
89946 点
帖子
1970
精华
12
在线时间
1933 小时
注册时间
2019-9-11
最后登录
2021-6-25

初级热心勋章

CDA网校 学生认证  发表于 2021-4-7 10:08:44 |显示全部楼层
本资源收录了机器学习课程用到的相关术语,涉及
  • 机器学习基础
  • 机器学习理论
  • Applied Math
  • SVM
  • Ensemble
  • DNN
  • Regularization
  • Matrix Factorization
  • Optimization
  • CNN
  • Auto EncoderRNN
  • Representation
  • Network Embedding
  • GAN
  • Adversarial Learning
  • Online Learning
  • Reinforcement Learning
  • AutoML
  • Graphic Model
  • Topic Model
  • MCMC
  • Mean-Field
  • non-parametric models

等。
    资源整理自网络,源地址:
https://aminer.cn/ml_taxonomy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


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 NeighborK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-dimensionVC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 ConditionsKKT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 RegularizationL2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 RegularizationL1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 DivergenceKL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 PriorWishart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 momentumNesterov 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
PCAPCA

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
SVDSVD

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) divergenceKL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 matrixjacobi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 productHadamard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-gramN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 NormF-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 DivergenceJS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 divergenceKL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 RegressionSoftmax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-LearningQ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

Yann LeCun   更多

The mnist database of handwritten digits   更多

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

ANOVA方差分析

Ronald Klein   更多

A new method for non-parametric multivariate analysis of variance   更多
Extrapolation外推法

Sergey Fomel  更多

A Riemannian Framework for Tensor Computing   更多
activation function激活函数

Jun Wang(王鈞)   更多

A new learning algorithm for blind source separation   更多

CIFAR-10

Boris Murmann   更多

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 neighborsK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

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 BoundHoeffding界

Qinbao Song(宋擒豹)   更多

Chernoff-Hoeffding Bounds for Applications with Limited Independence   更多
Chernoff BoundChernoff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 algorithmMetropolis-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 SchemeBlackwell-MacQueen桶法

Stephen G. Walker   更多

Some Developments of the Blackwell-MacQueen Urn Scheme   更多
De Finetti's theoremde 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



扫码关注CDA公众号,回复“术语表”,即可获取pdf




题库





关键词:机器学习 深度学习 中英对照 人工智能 对照表 机器学习专业术语表 深度学习专业术语表 人工智能专业术语表

已有 8 人评分经验 论坛币 学术水平 热心指数 信用等级 收起 理由
happy_287422301 + 100 对论坛有贡献
那年,那月… + 5 + 5 + 5 精彩帖子
remlus + 80 精彩帖子
oliyiyi + 100 精彩帖子
np84 + 100 精彩帖子
xujingtang + 80 精彩帖子
Cowboy_Hk + 1 + 1 + 1 精彩帖子
wwqqer + 100 + 5 + 5 + 5 精彩帖子

总评分: 经验 + 460  论坛币 + 100  学术水平 + 11  热心指数 + 11  信用等级 + 11   查看全部评分


CDA人工智能学院http://edu.cda.cn)专注于数据科学与人工智能技术的在线教育平台。内容涵盖数据分析、机器学习、深度学习、人工智能、TensorFlow、PyTorch、知识图谱等众多核心技术及其行业案例,自由灵活的在线学习方式,让每一个学员快速掌握AI时代最前沿的技术!
gudure 学生认证  发表于 2021-4-7 10:40:50 |显示全部楼层
感谢分享
回复

使用道具 举报

gudure 学生认证  发表于 2021-4-7 10:41:01 |显示全部楼层
回复

使用道具 举报

时光人 学生认证  发表于 2021-4-7 10:42:58 |显示全部楼层
很不错的内容
回复

使用道具 举报

xujingjun 发表于 2021-4-7 11:35:07 |显示全部楼层
回复

使用道具 举报

512661101 发表于 2021-4-7 12:25:32 |显示全部楼层
回复

使用道具 举报

escaflowne1985 在职认证  发表于 2021-4-7 13:56:40 |显示全部楼层
感谢分享~~~~~~么么哒
回复

使用道具 举报

512661101 发表于 2021-4-8 10:34:30 |显示全部楼层
回复

使用道具 举报

三重虫 发表于 2021-4-8 10:45:02 |显示全部楼层
回复

使用道具 举报

yujiangxiao 发表于 2021-4-8 12:37:19 |显示全部楼层
感谢分享!!
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 我要注册

京ICP备16021002-2号 京B2-20170662号 京公网安备 11010802022788号 论坛法律顾问:王进律师 知识产权保护声明   免责及隐私声明

GMT+8, 2021-6-25 18:13