Flake, Gary William and Pearlmutter, Barak A. (2000) Differentiating Functions of the Jacobian with Respect to the Weights. Advances in Neural Information Processing Systems, 12. pp. 435-441. ISSN 1049-5258

Preview

Download (113kB) | Preview

Abstract

For many problems, the correct behavior of a model depends not only on its input-output mapping but also on properties of its Jacobian matrix, the matrix of partial derivatives of the model's outputs with respect to its inputs. We introduce the J-prop algorithm, an efficient general method for computing the exact partial derivatives of a variety of simple functions of the Jacobian of a model with respect to its free parameters. The algorithm applies to any parametrized feedforward model, including nonlinear regression, multilayer perceptrons, and radial basis function networks.

Item Type:	Article
Keywords:	Differentiating Functions; Jacobian; Respect to the Weights;
Academic Unit:	Faculty of Science and Engineering > Computer Science Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	5484
Depositing User:	Barak Pearlmutter
Date Deposited:	13 Oct 2014 15:16
Journal or Publication Title:	Advances in Neural Information Processing Systems
Publisher:	Massachusetts Institute of Technology Press (MIT Press)
Refereed:	Yes
URI:
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads