No self-introduction
Loading
Profile
Follow
codes (7)
Outlier robust extreme learning machine for regression problems
no vote
The goal is to minimize L1 norm loss function and L2 norm output weight. For more details, please refer to the paper "Zhang K, Luo M. Outlier-robust extreme learning machine for regression problems[J]. Neurocomputing, 2015, 151: 1519-1527.".
wrfei01 1 0
1
SA_ SVM self learning support vector machine
no vote
Binary classifier based on & quot; self advising support vector machine, Yashar maali, Adel al jumaily, knowledge-based systems 52 (2013) 214 – 222 & quot; & nbsp; traindata is the digital matrix of predictive variable data. Traindata rows correspond to observations; columns correspond to features. Trainlabel is a label (1 or 0) that contains the column vector & nbsp; & nbsp; traindata of a known class. Each element of trainlabel specifies that the group corresponding to & nbsp; & nbsp; traindata row belongs to traindata, and trainlabel must have the same number of rows. &Nbsp; & nbsp; testdata is a numeric matrix that predicts variable data. Test data rows correspond to observations; test data columns correspond to observations features.Testlabel Is a label (1 or 0) that contains the column vector of a known class & nbsp; & nbsp; testdata. Each element of testlabel specifies the row to which the group corresponds & nbsp; & nbsp; testdata. Testdata and testlabel must have the same number of rows.
wrfei01 1 0
1
Extreme learning machine and adaptive sparse representation
no vote
The demonstration of ea-src algorithm in demo_ Classification_ In addition to the main algorithm, the main contribution of regularized elm using the computational efficient loo method (relm-loo) is also given_ "Classification" and "demo"_ It is demonstrated in regression; the regressor includes the regularized elm method with computational efficiency (relm-loo), which is given in the folder "/ utilities" named "regressor"; the folder & nbsp; '/ l1ls includes four representative sparse reconstruction algorithms; it includes two classification applications and one regression application.
wrfei01 1 0
1
Hybrid extreme learning machine and sparse representation
no vote
By combining extreme learning machine (ELM) and sparse representation (SRC) into a unified framework, the proposed hybrid classifier not only has the advantages of fast testing (ELM), but also shows significant classification accuracy (SRC). Test its ar face recognition, it achieves 95% high accuracy, better than elm (91%) and SRC (93.5%). The bridge between elm and Src is elm error classification measurement and adaptive selection.
wrfei01 1 0
1
Yan prtools matlab toolbox now includes 40 common pattern recognition algorithms
4.0
The YAN-PRTools matlab toolbox now includes 40 common pattern recognition a lgorithms:Feature processingmat2ftvec : Transform sample matrices to a feature matrixzscore : feature normalizationpca : PCAkpca : KPCAlda : LDAClassification
wrfei01 4 0
1
Multi class support vector machine classifier
no vote
Support vector machine (d-svm) based on tree graph is used to train data sets and perform multi class classification. The two main functions are: train_ DSVM: This is the function classify for training_ DSVM: This is a function for d-svm classification
wrfei01 1 0
1
Extreme learning machine for regression and binary classification problems
no vote
Extreme learning machine (with examples) based on MATLAB is used for regression and binary classification problems. Fast OOP MATLAB® implementation of Extreme Learning Machines (ELM) for both regression and binary classification problems.
wrfei01 1 0
1
No more~
Follows0
Fans0