The text below describes a short introduction to extreme learning machines (ELM) enlightened by new developed applications. It also includes an introduction to deep belief networks (DBN), slightly tuned in the pattern recognition problems. Essentially, the deep belief networks learn to extract invariant characteristics of an object, or, in other words, a DBN shows the ability to simulate how the brain recognizes patterns by the contrastive divergence algorithm and choosing a particular network configuration. Finally, it contains a strategy based on the extreme learning of the deep features, enhancing the recognition rate within the ELM approach, and concluding with successful experimental results in well-known benchmarks.
Keywords
Extreme Learning Machines, Restricted Boltzmann Machines, Deep Belief Networks, Deep learning
Conference
18th Iberoamerican Congress on Pattern Recognition (CIARP 2013), LNCS; Springer, November 2013
Cited by
Year 2016 : 1 citations
Huang, W. B., & Sun, F. C. (2016). Building feature space of extreme learning machine with sparse denoising stacked-autoencoder. Neurocomputing, 174, 60-71.
Year 2015 : 3 citations
Huang, Wen-bing, and Fu-chun Sun. "A Deep and Stable Extreme Learning Approach for Classification and Regression." Proceedings of ELM-2014 Volume 1. Springer International Publishing, 2015. 141-150.
Zeng, Y., Xu, X., Fang, Y., & Zhao, K. (2015, June). Traffic sign recognition using extreme learning classifier with deep convolutional features. In The 2015 international conference on intelligence science and big data engineering (IScIDE 2015), Suzhou, China.
Chen, L., Qu, H., Zhao, J., Chen, B., & Principe, J. C. (2015). Efficient and robust deep learning with Correntropy-induced loss function. Neural Computing and Applications, 1-13.
Year 2014 : 2 citations
Andrea Carolina Peres Kulaif, Técnicas de Regularização para Máquinas de Aprendizado Extremo, MSc thesis, Faculdade de Engenharia elétrica e da Computação, Universidade Estadual De Campinas, 2014
Le-le Cao, W. B. H., & Sun, F. C. (2014). A Deep and Stable Extreme Learning Approach for Classification and Regression?. Proceedings of ELM-2014 Volume 1: Algorithms and Theories, 3, 141.
