Task Decomposition Using Geometric Relation for Min-Max Modular SVMs
نویسندگان
چکیده
The min-max modular support vector machine (M-SVM) was proposed for dealing with large-scale pattern classification problems. M-SVM divides training data to several sub-sets, and combine them to a series of independent sub-problems, which can be learned in a parallel way. In this paper, we explore the use of the geometric relation among training data in task decomposition. The experimental results show that the proposed task decomposition method leads to faster training and better generalization accuracy than random task decomposition and traditional SVMs.
منابع مشابه
Incorporating Prior Knowledge into Task Decomposition for Large-Scale Patent Classification
With the adoption of min-max-modular support vector machines (SVMs) to solve large-scale patent classification problems, a novel, simple method for incorporating prior knowledge into task decomposition is proposed and investigated. Two kinds of prior knowledge described in patent texts are considered: time information, and hierarchical structure information. Through experiments using the NTCIR-...
متن کاملEfficient Text Categorization Using a Min-Max Modular Support Vector Machine
The min-max modular support vector machine (M-SVM) has been proposed for solving large-scale and complex multiclass classification problems. In this paper, we apply the M-SVM to multilabel text categorization and introduce two task decomposition strategies into M-SVMs. A multilabel classification task can be split up into a set of two-class classification tasks. These two-class tasks are to dis...
متن کاملApplying Spectral Clustering Algorithm on Min-max Modular Support Vector Machine
Through task decomposition and module combination, min-max modular support vector machines (M-SVMs) can be successfully used for different pattern classification tasks. A effective task decomposition strategy has been proved that is very critical to the final classification results. Based on a spectral clustering strategy, M-SVMs can divide the training data set of the original problem into sev...
متن کاملGender Recognition Using a Min-Max Modular Support Vector Machine
Considering the fast respond and high generalization accuracy of the min-max modular support vector machine (M-SVM), we apply M-SVM to solving the gender recognition problem and propose a novel task decomposition method in this paper. Firstly, we extract features from the face images by using a facial point detection and Gabor wavelet transform method. Then we divide the training data set into ...
متن کاملMulti-view Face Recognition with Min-Max Modular SVMs
Through task decomposition and module combination, minmax modular support vector machines (M-SVMs) can be successfully used for difficult pattern classification task. M-SVMs divide the training data set of the original problem to several sub-sets, and combine them to a series of sub-problems which can be trained more effectively. In this paper, we explore the use of M-SVMs in multi-view face re...
متن کامل