Adaptive sensor modelling and classification using a continuous restricted Boltzmann machine (CRBM)

Authors:
Tong Boon Tang;Alan F. Murray
Affiliations:
School of Engineering and Electronics, The University of Edinburgh, King's Buildings, Mayfield Road, Edinburgh EH9 3JL, UK;School of Engineering and Electronics, The University of Edinburgh, King's Buildings, Mayfield Road, Edinburgh EH9 3JL, UK
Venue:
Neurocomputing
Year:
2007

Citing 10
Cited 1

Probabilistic Visual Learning for Object Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Wireless integrated network sensors

Communications of the ACM
PicoRadio Supports Ad Hoc Ultra-Low Power Wireless Networking

Computer
Probabilistic Reasoning Models for Face Recognition

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Neural Networks: A Comprehensive Foundation (3rd Edition)

Neural Networks: A Comprehensive Foundation (3rd Edition)
Video-based face recognition using probabilistic appearance manifolds

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dynamic neural controllers for induction motor

IEEE Transactions on Neural Networks
Application of the recurrent multilayer perceptron in modeling complex process dynamics

IEEE Transactions on Neural Networks

Probabilistic neural computing with advanced nanoscale MOSFETs

Neurocomputing

Quantified Score

Hi-index	0.02

Visualization

Abstract

A probabilistic, ''neural'' approach to sensor modelling and classification is described, performing local data fusion in a wireless system for embedded sensors using a continuous restricted Boltzmann machine (CRBM). The sensor data clusters are non-Gaussian and their classification is non-linear. A CRBM is shown to be able to model complex data distributions and to adjust autonomously to measured sensor drift. Performance is compared with that of single layer and multilayer neural classifiers. It is shown that a CRBM can resolve the problem of catastrophic interference that is typical of associative memory based models.