A robust backpropagation learning algorithm for function approximation

Authors:
D. S. Chen;R. C. Jain
Affiliations:
Artificial Intelligence Lab., Michigan Univ., Ann Arbor, MI;-
Venue:
IEEE Transactions on Neural Networks
Year:
1994

Citing 0
Cited 16

TAO-robust backpropagation learning algorithm

Neural Networks
Improving the accuracy while preserving the interpretability of fuzzy function approximators by means of multi-objective evolutionary algorithms

International Journal of Approximate Reasoning
CPBUM neural networks for modeling with outliers and noise

Applied Soft Computing
Robust neural-fuzzy method for function approximation

Expert Systems with Applications: An International Journal
Hybrid robust approach for TSK fuzzy modeling with outliers

Expert Systems with Applications: An International Journal
Functional-link nets with genetic-algorithm-based learning for robust nonlinear interval regression analysis

Neurocomputing
Robust incremental growing multi-experts network

Applied Soft Computing
Hybrid robust support vector machines for regression with outliers

Applied Soft Computing
Robust identification of nonlinear complex systems using low complexity ANN and particle swarm optimization technique

Expert Systems with Applications: An International Journal
On maximum likelihood fuzzy neural networks

Fuzzy Sets and Systems
A novel function approximation based on robust fuzzy regression algorithm model and particle swarm optimization

Applied Soft Computing
Outliers detection in environmental monitoring databases

Engineering Applications of Artificial Intelligence
An energy-gain bounding approach to robust fuzzy identification

Automatica (Journal of IFAC)
Adaptive ore grade estimation method for the mineral deposit evaluation

Mathematical and Computer Modelling: An International Journal
Robust Learning Algorithm Based on Iterative Least Median of Squares

Neural Processing Letters
Pointwise probability reinforcements for robust statistical inference

Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

The backpropagation (BP) algorithm allows multilayer feedforward neural networks to learn input-output mappings from training samples. Due to the nonlinear modeling power of such networks, the learned mapping may interpolate all the training points. When erroneous training data are employed, the learned mapping can oscillate badly between data points. In this paper we derive a robust BP learning algorithm that is resistant to the noise effects and is capable of rejecting gross errors during the approximation process. The spirit of this algorithm comes from the pioneering work in robust statistics by Huber and Hampel. Our work is different from that of M-estimators in two aspects: 1) the shape of the objective function changes with the iteration time; and 2) the parametric form of the functional approximator is a nonlinear cascade of affine transformations. In contrast to the conventional BP algorithm, three advantages of the robust BP algorithm are: 1) it approximates an underlying mapping rather than interpolating training samples; 2) it is robust against gross errors; and 3) its rate of convergence is improved since the influence of incorrect samples is gracefully suppressed