2009 · 35 citations · 19 references
ComputingComputer EngineeringComputer ScienceArtificial IntelligenceMachine LearningNeural EngineeringBayesian LearningFault DetectionNeural NetworksNoisePattern RecognitionProbabilistic Machine LearningBayesian NetworksBayesian Neural NetworksEarly StoppingEarly Stopping RulesNeural Network-based DiagnosisNoise InjectionSimulation StudiesWeight Decay
We studied the effect of noise injection in overcoming the problem of overtraining in the training of artificial neural networks (ANNs) in comparison with other common approaches for overcoming this problem such as early stopping of the ANN training process and weight decay (which is similar to Bayesian artificial neural networks). We found from simulation studies and studies of a computer-aided diagnosis application that noise injection is effective in overcoming overtraining and is as effective as, or even more effective than, early stopping and weight decay.
19
Creating artificial neural networks that generalize
Jocelyn Sietsma, R.J.F. Dow · Neural Networks · 1991 · 598 citations