A Hybrid Online Sequential Extreme Learning Machine with Simplified Hidden Network
Meng Joo Er, L. Y. Zhai, Linn San · 2012
In this paper, a novel learning algorithm termed Hybrid Online Sequential Extreme Learning Machine (HOS- ELM) is proposed. The proposed HOS-ELM algorithm is a fusion of the Online Sequential Extreme Learning Machine (OS-ELM) and the Minimal Resource Allocation Network (MRAN). It is capable of reducing the number of hidden nodes in Single-hidden Layer Feed-forward Neural Networks (SLFNs) with Radial Basis Function (RBF) by virtue of adjustment in node allocation and pruning capability. Simulation results show that the generalization performance of the proposed HOS-ELM is comparable to the original OS- ELM with significant reduction in the number of hidden nodes. Index Terms—single-hidden layer feed-forward neural networks (SLFN), minimal resource allocation network (MRAN), extreme learning machine (ELM), neural networks, online sequential learning