Search research articles

Search research articles

Related Experiment Videos

Adaptive filtering with the self-organizing map: a performance comparison.

Guilherme A Barreto¹, Luís Gustavo M Souza

¹Department of Teleinformatics Engineering, Federal University of Ceará, Av. Mister Hull, S/N-C.P. 6005, CEP 60455-760, Center of Technology, Campus do Pici, Fortaleza, Ceará, Brazil. guilherme@deti.ufc.br

Neural Networks : the Official Journal of the International Neural Network Society

|July 1, 2006

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A stochastic variational framework for Recurrent Gaussian Processes models.

Neural networks : the official journal of the International Neural Network Society·2019

Same author

Condition monitoring of 3G cellular networks through competitive neural models.

IEEE transactions on neural networks·2005

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Self-Organizing Maps (SOMs) offer a powerful approach to nonlinear adaptive filtering. New RBF-based filters using Vector-Quantized Temporal Associative Memory (VQTAM) with SOMs outperform MLP-based filters in complex tasks.

Area of Science:

Artificial Intelligence
Machine Learning
Signal Processing

Background:

Nonlinear adaptive filtering is crucial for many signal processing applications.
Existing methods often struggle with complex nonlinear dynamics.
Self-Organizing Maps (SOMs) present a potential solution for learning input-output mappings.

Purpose of the Study:

To evaluate the Self-Organizing Map (SOM) as a tool for nonlinear adaptive filtering.
To introduce novel Radial Basis Function (RBF)-based nonlinear filters utilizing SOMs.
To compare the performance of SOM-based filters against established linear and neural network filters.

Main Methods:

A comprehensive survey of SOM-based architectures for learning input-output mappings.
Development of two RBF-based nonlinear filters using Vector-Quantized Temporal Associative Memory (VQTAM) with SOMs.

Related Experiment Videos

Comparative analysis against Finite Impulse Response/Least Mean Squares (FIR/LMS) and Multi-Layer Perceptron (MLP)-based filters.

Main Results:

SOM-based filters demonstrate effectiveness in nonlinear channel equalization.
These filters also show superior performance in inverse modeling tasks.
Performance of SOM-based filters consistently surpasses that of MLP-based filters.

Conclusions:

SOMs are a feasible and high-performing tool for nonlinear adaptive filtering.
The proposed VQTAM-based SOM filters offer a significant advancement over existing methods.
SOM-based approaches provide a robust alternative for complex nonlinear signal processing challenges.