Improving generalization of MLPs with multi-objective optimization. (English) Zbl 1003.68627

Summary: This paper presents a new learning scheme for improving generalization of multilayer perceptrons. The algorithm uses a multi-objective optimization approach to balance between the error of the training data and the norm of network weight vectors to avoid overfitting. The results are compared with support vector machines and standard backpropagation.


68U99 Computing methodologies and applications
68T05 Learning and adaptive systems in artificial intelligence
Full Text: DOI