Rough Neuron based on Pattern Space Partitioning

Authors:
Sandeep Chandana;Rene V. Mayorga
Affiliations:
Faculty of Engineering, University of Calgary, Canada;Faculty of Engineering, University of Regina, Canada
Venue:
Neurocomputing
Year:
2011

Citing 6
Cited 1

A neurocomputational perspective

A neurocomputational perspective
Comparison of neofuzzy and rough neural networks

Information Sciences: an International Journal
Rough Sets: Theoretical Aspects of Reasoning about Data

Rough Sets: Theoretical Aspects of Reasoning about Data
Design of Rough Neurons: Rough Set Foundation and Petri Net Model

ISMIS '00 Proceedings of the 12th International Symposium on Foundations of Intelligent Systems
Rough Approximation based Neuro Fuzzy Inference System: A novel approach to Approximation and Error Estimation

HIS '05 Proceedings of the Fifth International Conference on Hybrid Intelligent Systems
Rough Neural Networks for Complex Concepts

RSFDGrC '07 Proceedings of the 11th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing

Feedforward neural networks for compound signals

Theoretical Computer Science

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper proposes a novel method of combining Rough concepts with Neural Computation. The proposed New Rough Neuron consists of, one Lower Bound Neuron and another Boundary Neuron. The combination is designed in a way such that the Boundary Neuron deals only with the random and unpredictable part of the applied signal. This division results in an improved rate of error convergence in the back propagation of the neural network along with an improved parameter approximation during the network learning process. Some testing results have been presented, and performance compared with some of the prevalent designs.