Learning neural networks with noisy inputs using the errors-in-variables approach

Currently, most learning algorithms for neural-network modeling are based on the output error approach, using a least squares cost function. This method provides good results when the network is trained with noisy output data and known inputs. Special care must be taken, however, when training the n...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2000-03, Vol.11 (2), p.402-414
Main Authors: Van Gorp, J., Schoukens, J., Pintelon, R.
Format: Article
Language:English
Subjects:
Algorithms
Computational efficiency
Constraint optimization
Cost function
Curve fitting
Fuzzy logic
Learning
Least squares method
Least squares methods
Networks
Neural networks
Noise
Optimization methods
Robust stability
Stochastic resonance
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Currently, most learning algorithms for neural-network modeling are based on the output error approach, using a least squares cost function. This method provides good results when the network is trained with noisy output data and known inputs. Special care must be taken, however, when training the network with noisy input data, or when both inputs and outputs contain noise. This paper proposes a novel cost function for learning NN with noisy inputs, based on the errors-in-variables stochastic framework. A learning scheme is presented and examples are given demonstrating the improved performance in neural-network curve fitting, at the cost of increased computation time.
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/72.839010