A Class-Incremental Learning Method Based on One Class Support Vector Machine

A method based on one class support vector machine (OCSVM) is proposed for class incremental learning. Several OCSVM models divide the input space into several parts. Then, the 1VS1 classifiers are constructed for the confuse part by using the support vectors. During the class incremental learning process, the OCSVM of the new class is trained at first. Then the support vectors of the old classes and the support vectors of the new class are reused to train 1VS1 classifiers for the confuse part. In order to bring more information to the certain support vectors, the support vectors are at the boundary of the distribution of samples as much as possible when the OCSVM is built. Compared with the traditional methods, the proposed method retains the original model and thus reduces memory consumption and training time cost. Various experiments on different datasets also verify the efficiency of the proposed method.

[1]  Gert Cauwenberghs,et al.  Incremental and Decremental Support Vector Machine Learning , 2000, NIPS.

[2]  Xin Xu,et al.  A Class-Incremental Learning Method for Multi-Class Support Vector Machines in Text Classification , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[3]  Saeid Homayouni,et al.  Anomaly Detection in Hyperspectral Images Based on an Adaptive Support Vector Method , 2011, IEEE Geoscience and Remote Sensing Letters.

[4]  Yuhua Li,et al.  Selecting Critical Patterns Based on Local Geometrical and Statistical Information , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Wang Chun-li.  Study on Class Incremental Learning Algorithm Based on Hyper-sphere Support Vector Machines , 2008 .

[6]  Noureddine Ellouze,et al.  Improved one-class SVM classifier for sounds classification , 2007, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance.

[7]  Jay Lee,et al.  A modified support vector data description based novelty detection approach for machinery components , 2013, Appl. Soft Comput..

[8]  Huangang Wang,et al.  Parameter Selection of Gaussian Kernel for One-Class SVM , 2015, IEEE Transactions on Cybernetics.

[9]  Roger Xu,et al.  Model Selection for Anomaly Detection in Wireless Ad Hoc Networks , 2007, 2007 IEEE Symposium on Computational Intelligence and Data Mining.

[10]  H. Karimi,et al.  A Mahalanobis Hyperellipsoidal Learning Machine Class Incremental Learning Algorithm , 2014 .

[11]  Huan Liu,et al.  Handling concept drifts in incremental learning with support vector machines , 1999, KDD '99.

[12]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.