A Neural Network Model for Large-Scale Stream Data Learning Using Locally Sensitive Hashing

Recently, mining knowledge from stream data such as access logs of computer, commodity distribution data, sales data, and human lifelog have been attracting many attentions. As one of the techniques suitable for such an environment, active learning has been studied for a long time. In this work, we propose a fast learning technique for neural networks by introducing Locality Sensitive Hashing (LSH) and a local learning algorithm with LSH in RBF networks.

[1]  Yongdong Zhang,et al.  An improved method of locality sensitive hashing for indexing large-scale and high-dimensional features , 2013, Signal Process..

[2]  Shigeo Abe,et al.  Incremental learning of feature space and classifier for face recognition , 2005, Neural Networks.

[3]  Ting Li,et al.  Locality sensitive hashing based searching scheme for a massive database , 2008, IEEE SoutheastCon 2008.

[4]  Raymond J. Mooney,et al.  Diverse ensembles for active learning , 2004, ICML.

[5]  Shaoning Pang,et al.  Incremental Learning of Chunk Data for Online Pattern Classification Systems , 2008, IEEE Transactions on Neural Networks.

[6]  Na Sun,et al.  A Modified Incremental Learning Approach for Data Stream Classification , 2012, 2012 Sixth International Conference on Internet Computing for Science and Engineering.

[7]  Kyung Mi Lee,et al.  Similar pair identification using locality-sensitive hashing technique , 2012, The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems.