An Online Incremental Semi-Supervised Learning Method
Furao Shen, Hui Jing Yu, Youki Kamiya, Osamu Hasegawa · Journal of Advanced Computational Intelligence and Intelligent Informatics · 2010
Using labeled data and large amounts of unlabeled data, our proposed online incremental semisupervised learning automatically learns the topology of input data distribution without prior knowledge of numbers of nodes or network structure. Using labeled data, it labels generated nodes and divides a learned topology into substructures corresponding to classes. Node weights used as prototype vectors enable classification. New labeled or unlabeled data is added incrementally to the system during learning. Experimental results for artificial and real-world data show that this learning efficiently learns online incremental tasks even in noisy and non-stationary environments.