1,贝叶斯算法:
朴素贝叶斯算法(Nalve Bayes)
高斯朴素贝叶斯算法(Caussian Naive Bayes)
多项式朴素贝叶斯算法(Multinomial Naive
Baves)
AODE算法(Averaged One-Dependence
Estimetors(AODE)
贝叶斯信念网络(Bayesien Bellef
Network(BBN))
贝叶斯网络(Bayesian Network(BN))
2,正则化算法:
岭回归(Ridge Regression)
LASSO算法(Least Absolute Shrinkege and
Selection Operator(LASSO))
弹性网络(Elastic Net)
最小角回归算法(Least Angle
Regression(LARS))
3,关联规则学习:
(Cubist)
(One Rule(OneR))
(Zero Rule(ZeroR))
(Repeated Incremental Pruning to Produce
Error Reduction(RIPPER))
4,决策树算法:
分类和回归树(Classfficetion and Regression
Tree(CART))
IDS算法(Iterative Dichotomiser 3(D3)
C4.5)
C 5.0)
CHAID算法(Chi-squared Automatic
Interaction Detection(CHAlD))
单层决策树(Decision Stump)
条件决策树(Conditional Decislon Trees
(M5)
5,模型融合算法:
随机森林(Random Forest)
(Gredient Boosting Machines(GBM))
(Boosting)
堆叠泛化(融合)(Stacked
Generallzation(Blending))
(Bootstrepped Aggregetion(Bagging))
(AdaBoost)
6,回归算法:
线性回归(Linear Regression)
逐步回归(Stepwlse Regression)
罗辑回归(Logistic Resression)
普通最小二乘回归(Orcinary Least Squares Regression(OLSR))
局部估计平滑散点图(Locally Estimated Scatterplot Smoothing(LOESS))
多元自适应回归样条法(Multivariate Adaptlve Regression Splines(MARS))
7,基于实例的算法:
k-近邻算法(k-Nearest Neighbor (kNN))
学习矢量量化算法(Leaming Vector Quentizetion(LvQ))
自组织映射算法(Self-orsanizing Map(SQM)
局部加权学习算法(Locally Weighted Leerning(LWL))
8,聚类算法:
k-均值(k-Means)
k一中值(k-Medians
最大期望算法(Expectation Meximizatlon)
分层聚类算法(Hierarchical Clustering)
9,人工神经网络:
径向基函数网络(Radial Basis Function Network (REFN))
感知机(Perceptron)
Hapfiek网路(Hopfeld Network)
BP神经网络(Back-Prapegation)
10,深度学习算法:
深度玻尔兹曼机(Deep Boltzman Machine (DEM))
深度置信网络(Deep Bellef Networks(DEN))
卷积神经网络(Convclutlonal Neural Network(CNN))
栈式自编码算法(Stacked Auto-Encoders)
11,降维算法:
主成分分析(Principal Component
Analysis(PCA))
主成分回归(Principal Component
Regressian(PCR))
偏最小二乘回归(Partial Least Squares
Regression(PLSR))
萨蒙映射(Sammon Mapping)
多维尺度分析法(Multiclmensional
Scaling(MDS))
投影跟踪法(Proiection Pursuit)
偏最小二乘判别分析法(Partial Least Squares
Discriminant Analysis)
混合判别分析法(Mkture Discriminant
Analysis(MDA))
二次判别分析法(Quadratic Discriminant
Analvsis(osA))
(Regularized Discriminent Analysls(RDA))
灵活判别分析法(Flexible Discriminant
Analysis(FDA))
线性判别分析法(LInear Dlscriminent
Analysis(LDA))