Open AccessEarly Stopping Criteria for Levenberg-Marquardt Based Neural Network Training Optimization
Author(s) -
Azizah Suliman,
Батырхан Омаров
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i4.36.25382
Subject(s) - overtraining , early stopping , levenberg–marquardt algorithm , artificial neural network , training (meteorology) , artificial intelligence , computer science , machine learning , pattern recognition (psychology) , medicine , geography , meteorology , athletes , physical therapy
In this research we train a direct distributed neural network using Levenberg-Marquardt algorithm. In order to prevent overtraining, we proposed correctly recognized image percentage based on early stop condition and conduct the experiments with different stop thresholds for image classification problem. Experiment results show that the best early stop condition is 93% and other increase in stop threshold can lead to decrease in the quality of the neural network. The correct choice of early stop condition can prevent overtraining which led to the training of a neural network with considerable number of hidden neurons.