LAUSR

A novel online sequential extreme learning machine (ELM) algorithm with regularization mechanism in a unified framework is proposed in this paper. This algorithm is called timeliness online regularized extreme learning machine (TORELM). Like the timeliness managing extreme learning machine (TMELM) which incorporates timeliness management scheme into ELM approach for the incremental samples, TORELM also processes data one-by-one or chunk-by-chunk under the similar framework, while the newly incremental data could be prior to the historical data by maximizing the contribution of the newly increasing training data. Furthermore, in consideration of the disproportion between empirical risk and structural risk in some traditional learning methods, we add regularization technique to the timeliness scheme of TORELM through the use of a weight factor to balance them to achieve better generalization performance. Therefore, TORELM may has its unique feature of higher generalization capability with a small testing error while implementing online sequential learning. And the simulation results show that TORELM performs better than other ELM algorithms.