Improving the error backpropagation algorithm with a modified error function

Authors:
Sang-Hoon Oh
Affiliations:
Res. Dept., Electron. & Telecommun. Res. Inst., Taejon
Venue:
IEEE Transactions on Neural Networks
Year:
1997

Citing 0
Cited 9

Deterministic convergence of an online gradient method for neural networks

Journal of Computational and Applied Mathematics - Selected papers of the international symposium on applied mathematics, August 2000, Dalian, China
Computational Cost Reduction by Selective Attention for Fast Speaker Adaptation in Multilayer Perceptron

IEA/AIE '02 Proceedings of the 15th international conference on Industrial and engineering applications of artificial intelligence and expert systems: developments in applied artificial intelligence
A Hybrid Recurrent Neural Network for Machining Process Modeling

ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
When does online BP training converge?

IEEE Transactions on Neural Networks
The development of improved back-propagation neural networks algorithm for predicting patients with heart disease

ICICA'10 Proceedings of the First international conference on Information computing and applications
Letters: Error back-propagation algorithm for classification of imbalanced data

Neurocomputing
Handwritten digit recognition with kernel-based LVQ classifier in input space

ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Hidden node pruning of multilayer perceptrons based on redundancy reduction

ICHIT'11 Proceedings of the 5th international conference on Convergence and hybrid information technology
Improvements to the conventional layer-by-layer BP algorithm

ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This letter proposes a modified error function to improve the error backpropagation (EBP) algorithm of multilayer perceptrons (MLPs) which suffers from slow learning speed. To accelerate the learning speed of the EBP algorithm, the proposed method reduces the probability that output nodes are near the wrong extreme value of sigmoid activation function. This is acquired through a strong error signal for the incorrectly saturated output node and a weak error signal for the correctly saturated output node. The weak error signal for the correctly saturated output node, also, prevents overspecialization of learning for training patterns. The effectiveness of the proposed method is demonstrated in a handwritten digit recognition task