"Orthogonal Bases Are the Best: A Theorem Justifying Bruno Apolloni's H" by Jaime Nava and Vladik Kreinovich

Menu

Skip to main content

Departmental Technical Reports (CS)

Orthogonal Bases Are the Best: A Theorem Justifying Bruno Apolloni's Heuristic Neural Network Idea

Jaime Nava, The University of Texas at El PasoFollow
Vladik Kreinovich, The University of Texas at El PasoFollow

Publication Date

6-2011

Comments

Technical Report: UTEP-CS-11-34

To appear in Journal of Uncertain Systems, 2012, Vol. 6, No. 2.

Abstract

One of the main problems with neural networks is that they are often very slow in learning the desired dependence. To speed up neural networks, Bruno Apolloni proposed to othogonalize neurons during training, i.e., to select neurons whose output functions are orthogonal to each other. In this paper, we use symmetries to provide a theoretical explanation for this heuristic idea.

Find in your library

Included in

Computer Engineering Commons

COinS