Extended Hierarchical Extreme Learning Machine with Multilayer Perceptron

The Deep Learning approach provides a high performance of classification, especially when invoking image classification problems. However, a shortcoming of the traditional Deep Learning method is the large time scale of training. The hierarchical extreme learning machine (H-ELM) framework was based on the hierarchical learning architecture of multilayer perceptron to address the problem. H-ELM is composed of two parts; the first entails unsupervised multilayer encoding, and the second is the supervised feature classification. H-ELM can give a higher accuracy rate than the traditional ELM. However, there still remains room to enhance its classification performance. This paper therefore proposes a new method termed the extending hierarchical extreme learning machine (EH-ELM), which extends the number of layers in the supervised portion of the H-ELM from a single layer to multiple layers. To evaluate the performance of the EH-ELM, the various classification datasets were studied and compared with the H-ELM and the multilayer ELM, as well as various state-of-the-art such deep architecture methods. The experimental results show that the EH-ELM improved the accuracy rates over most other methods.