This paper points out some drawbacks and proposes some modifications to the conventional layer-by-layer BP algorithm. In particular, we present a new perspective to the learning rate, which is to use a heuristic rule to define the learning rate so as to update the weights. Meanwhile, to pull the algorithm out of saturation area and prevent it from converging to a local minimum, a momentum term is introduced to the former algorithm. And finally the effectiveness and efficiency of the proposed method are demonstrated by two benchmark examples. © Springer-Verlag Berlin Heidelberg 2005.
CITATION STYLE
Li, X. Q., Han, F., Lok, T. M., Lyu, M. R., & Huang, G. B. (2005). Improvements to the conventional layer-by-layer BP algorithm. In Lecture Notes in Computer Science (Vol. 3645, pp. 189–198). Springer Verlag. https://doi.org/10.1007/11538356_20
Mendeley helps you to discover research relevant for your work.