The Development and Analysis of Analytic Method as Alternative for Backpropagation in Large-Scale Multilayer Neural Networks
2014 (English)In: ADVCOMP 2014, The Eighth International Conference on Advanced Engineering Computing and Applications in Sciences, 2014, 46-49 p.Conference paper (Refereed)
This paper presents a least-square based analytic solution of the weights of a multilayer feedforward neural network with a single hidden layer and a sigmoid activation function, which today constitutes the most common type of artificial neural networks. This solution has the potential to be effective for large-scale neural networks with many hidden nodes, where backpropagation is known to be relatively slow. At this stage, more research is required to improve the generalization abilities of the proposed method.
Place, publisher, year, edition, pages
2014. 46-49 p.
analytic; FNN; large-scale; least square method; neural network; sigmoid
Research subject Computer Science
IdentifiersURN: urn:nbn:se:uu:diva-235742ISBN: 978-1-61208-354-4OAI: oai:DiVA.org:uu-235742DiVA: diva2:761789
The Proceedings of the Eighth International Conference on Advanced Engineering Computing and Applications in Sciences, ADVCOMP 2014, Rome, Italy, August 2014