[PS][PS] Improving the convergence of back-propagation learning with second order methods

S Becker, Y Le Cun - … of the 1988 connectionist models summer …, 1988 - yann.lecun.com
Back-propagation has proven to be a robust algorithm for difficult connectionist learning
problems. However, as with many gradient based optimization methods, it converges slowly.
We describe an extension of the back-propagation algorithm which uses a simple
approximation to the second derivative terms. This method is shown to reduce the required
number of iterations to learn a random classification problem, with only a small increase in
the complexity of each iteration. The back-propagation learning algorithm for multilayer …

[PDF][PDF] Improving the Convergence of Back-Propagation Learning with

S Becker, Y le Cun - 1988 - researchgate.net
Back-propagation has proven to be a robust algorithm for difficult connectionist learning
problems. However, as with many gradient based optimization methods, it converges slowly.
We describe an extension of the back-propagation algorithm which uses a simple
approximation to the second derivative terms. This method is shown to reduce the required
number of iterations to learn a random classification problem, wıth only a small increase in
the complex-ity of each iteration. The back-propagation learning algorithm for multilayer …
Showing the best results for this search. See all results