A novel progressive learning technique for multi-class classification

NEUROCOMPUTING

卷:207

Article

Venkatesan, Rajasekar¹  Er, Meng Joo¹ 

[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore, Singapore

关键词: Classification;    Machine learning;    Multi-class;    Sequential learning;    Progressive learning;   

DOI  :  10.1016/j.neucom.2016.05.006

来源: Elsevier

【 摘 要 】

In this paper, a progressive learning technique for multi-class classification is proposed. This newly developed learning technique is independent of the number of class constraints and it can learn new classes while still retaining the knowledge of previous Classes. Whenever a new class (non-native to the knowledge learnt thus far) is encountered, the neural network structure gets remodeled automatically by facilitating new neurons and interconnections, and the parameters are calculated in such a way that it retains the knowledge learnt thus far. This technique is suitable for real-world applications where the number of classes is often unknown and online learning from real-time data is required. The consistency and the complexity of the progressive learning technique are analyzed. Several standard datasets are used to evaluate the performance of the developed technique. A comparative study shows that the developed technique is superior. (C) 2016 Elsevier B.V. All rights reserved.

【 授权许可】

Free