Skip to Main Content
ASME Press Select Proceedings

Intelligent Engineering Systems through Artificial Neural Networks Volume 18

Cihan H. Dagli
Cihan H. Dagli
Search for other works by this author on:
No. of Pages:
ASME Press
Publication date:

The convergence of a Multilayer Perceptron (MLP) to a global minimum error in the backpropagation algorithm can be accelerated by introducing the representation of a weight search space, according to the Riemannian geometry, which considers the curvature of this space. The trajectory of the search vector at the training phase is modified by a “force” originated by this curvature. The main concept is developed from the Einstein's General Relativity theory, and the search space (or manifold) must be controlled by parameters like spatial density and scale factor, modifying the gradient descent in the backpropagation algorithm. Some preliminary results show the weights initialization much closer from the final solution, at few epochs, rather than the normal MLP, for an application related here.

This content is only available via PDF.
Close Modal
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close Modal
Close Modal