Skip to Main Content
Skip Nav Destination
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.

1 Introduction
2 The Weight Search Space
3 The Riemannian Weight Space Model
4 Obtaining the Metric Tensor
5 Coordinates Transformation and the Gradient Expression
6 Gradient Descent in the Riemannian Space
7 Application and Results
8 Conclusion
This content is only available via PDF.
You do not currently have access to this chapter.
Close Modal

or Create an Account

Close Modal
Close Modal