Comments on "Backpropagation Algorithms for a Broad Class of Dynamic Networks

Author

Endisch, Christian ; Stolze, Peter ; Hackl, Christoph ; Schröder, Dierk

Author_Institution

Inst. for Electr. Drive Syst., Tech. Univ. of Munich, Munich

Volume

20

Issue

3

fYear

2009

fDate

3/1/2009 12:00:00 AM

Firstpage

540

Lastpage

541

Abstract

"For original paper see O. De Jesus, .ibid., vol. 18, no. 1, p.14-27,(2007)",. In a recent paper, De Jesus proposed a general framework for describing dynamic neural networks. Gradient and Jacobian calculations were discussed based on backpropagation-through-time (BPTT) algorithm and real-time recurrent learning (RTRL). Some errors in the paper of De Jesus bring difficulties for other researchers who want to implement the algorithms. This comments paper shows the critical parts of the publication and gives errata to facilitate understanding and implementation.

Keywords

Jacobian matrices; backpropagation; gradient methods; recurrent neural nets; Jacobian calculation; backpropagation-through-time algorithm; dynamic neural network; gradient calculation; real-time recurrent learning; recurrent neural network; Backpropagation algorithms; Computer languages; Equations; Jacobian matrices; Neural networks; Neurons; Recurrent neural networks; Sections; System identification; Backpropagation-through-time (BPTT); dynamic neural network; layered digital dynamic network (LDDN); real-time recurrent learning (RTRL); recurrent neural network; Algorithms; Neural Networks (Computer);

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2009.2013243

Filename

4781588