Training Feedforward Neural Networks: An Algorithm Giving Improved Generalization

✍ Scribed by Charles W. Lee

• Publisher: Elsevier Science
• Year: 1997
• Tongue: English
• Weight: 711 KB
• Volume: 10
• Category: Article
• ISSN: 0893-6080
• DOI: 10.1016/s0893-6080(96)00071-8

✦ Synopsis

An algorithm is derived for supervised training in mtdtilayer feedforwardneural networks. Relative to the gradient descent backpropagation algorithm it appears to give bothfaster convergence and improved generalization, whilst preserving the system of backpropagating errors throughthe network.