A fast learning algorithm for multi-layer extreme learning machine
- 1 October 2014
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Extreme learning machine (ELM) is an efficient training algorithm originally proposed for single-hidden layer feedforward networks (SLFNs), of which the input weights are randomly chosen and need not to be fine-tuned. In this paper, we present a new stack architecture for ELM, to further improve the learning accuracy of ELM while maintaining its advantage of training speed. By exploiting the hidden information of ELM random feature space, a recovery-based training model is developed and incorporated into the proposed ELM stack architecture. Experimental results of the MNIST handwriting dataset demonstrate that the proposed algorithm achieves better and much faster convergence than the state-of-the-art ELM and deep learning methods.Keywords
This publication has 10 references indexed in Scilit:
- Extreme Learning Machine for Regression and Multiclass ClassificationIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012
- Human face recognition based on multidimensional PCA and extreme learning machinePattern Recognition, 2011
- Leukocyte image segmentation by visual attention and extreme learning machineNeural Computing & Applications, 2011
- Human action recognition using extreme learning machine based on visual vocabulariesNeurocomputing, 2010
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- Enhanced random search based incremental extreme learning machineNeurocomputing, 2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden NodesIEEE Transactions on Neural Networks, 2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998