BAYESIAN INFERENCE IN A DISTRIBUTED ASSOCIATIVE NEURAL NETWORK FOR ADAPTIVE SIGNAL PROCESSING

Qianglong Zeng, Ganwen Zeng

2006

Abstract

The primary advantages of high performance associative memory model are its ability to learn fast, store correctly, retrieve information similar to the human “content addressable” memory and it can approximate a wide variety of non-linear functions. Based on a distributed associative neural network, a Bayesian inference probabilistic neural network is designed implementing the learning algorithm and the underlying basic mathematical idea for the adaptive noise cancellation. Simulation results using speech corrupted with low signal to noise ratio in telecommunication environment shows great signal enhancement. A system based on the described method can store words and phrases spoken by the user in a communication channel and subsequently recognize them when they are pronounced as connected words in a noisy environment. The method guarantees system robustness in respect to noise, regardless of its origin and level. New words, pronunciations, and languages can be introduced to the system in an incremental, adaptive mode.

References

  1. Zeng, G., and Dan, H., Distributed Associative Neural Network Model Approximates Bayesian Inference, Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE 2002), pages 97-103, St. Louis, Missouri, Nov 2002.
  2. Jensen, F., The book Bayesian Networks and Decision Diagrams, Springer. 2001.
Download


Paper Citation


in Harvard Style

Zeng Q. and Zeng G. (2006). BAYESIAN INFERENCE IN A DISTRIBUTED ASSOCIATIVE NEURAL NETWORK FOR ADAPTIVE SIGNAL PROCESSING . In Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 978-972-8865-61-0, pages 177-181. DOI: 10.5220/0001202101770181


in Bibtex Style

@conference{icinco06,
author={Qianglong Zeng and Ganwen Zeng},
title={BAYESIAN INFERENCE IN A DISTRIBUTED ASSOCIATIVE NEURAL NETWORK FOR ADAPTIVE SIGNAL PROCESSING},
booktitle={Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2006},
pages={177-181},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001202101770181},
isbn={978-972-8865-61-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - BAYESIAN INFERENCE IN A DISTRIBUTED ASSOCIATIVE NEURAL NETWORK FOR ADAPTIVE SIGNAL PROCESSING
SN - 978-972-8865-61-0
AU - Zeng Q.
AU - Zeng G.
PY - 2006
SP - 177
EP - 181
DO - 10.5220/0001202101770181