Fully complex extreme learning machine
| Autor: | Narasimhan Sundararajan, Ming-Bin Li, Guang-Bin Huang, Paramasivan Saratchandran |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Artificial neural network
Wake-sleep algorithm Computer science Active learning (machine learning) business.industry Cognitive Neuroscience Computer Science::Neural and Evolutionary Computation Stability (learning theory) Generalization error Backpropagation Computer Science Applications Physics::Plasma Physics Artificial Intelligence Feedforward neural network Radial basis function Artificial intelligence business Extreme learning machine |
| Zdroj: | Neurocomputing. 68:306-314 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2005.03.002 |
| Popis: | Recently, a new learning algorithm for the feedforward neural network named the extreme learning machine (ELM) which can give better performance than traditional tuning-based learning methods for feedforward neural networks in terms of generalization and learning speed has been proposed by Huang et al. In this paper, we first extend the ELM algorithm from the real domain to the complex domain, and then apply the fully complex extreme learning machine (C-ELM) for nonlinear channel equalization applications. The simulation results show that the ELM equalizer significantly outperforms other neural network equalizers such as the complex minimal resource allocation network (CMRAN), complex radial basis function (CRBF) network and complex backpropagation (CBP) equalizers. C-ELM achieves much lower symbol error rate (SER) and has faster learning speed. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect