In this paper a high speed neural network classifier based on extremelearning machines for multi-label classification problem is proposed anddis-cussed. Multi-label classification is a superset of traditional binary andmulti-class classification problems. The proposed work extends the extremelearning machine technique to adapt to the multi-label problems. As opposed tothe single-label problem, both the number of labels the sample belongs to, andeach of those target labels are to be identified for multi-label classificationresulting in in-creased complexity. The proposed high speed multi-labelclassifier is applied to six benchmark datasets comprising of differentapplication areas such as multi-media, text and biology. The training time andtesting time of the classifier are compared with those of the state-of-the-artsmethods. Experimental studies show that for all the six datasets, our proposedtechnique have faster execution speed and better performance, therebyoutperforming all the existing multi-label clas-sification methods.
展开▼
