Convergence analysis of the Quickprop method

Author

Vrahatis, M.N. ; Magoulas, G.D. ; Plagianakos, V.P.

Author_Institution

Dept. of Math., Patras Univ., Greece

Volume

2

fYear

1999

fDate

36342

Firstpage

1209

Abstract

A mathematical framework for the convergence analysis of the well known Quickprop method is described. The convergence of this method is analyzed. Furthermore, we present modifications of the algorithm that exhibit improved convergence speed and stability and at the same time, alleviate the use of heuristic learning parameters. Simulations are conducted to compare and evaluate the performance of a proposed modified Quickprop algorithm with various popular training algorithms. The results of the experiments indicate that the increased convergence rates, achieved by the proposed algorithm, affect by no means its generalization capability and stability

Keywords

Newton method; character recognition; convergence; feedforward neural nets; generalisation (artificial intelligence); image texture; learning (artificial intelligence); pattern classification; stability; Quickprop method; convergence analysis; convergence rates; convergence speed; training algorithms; Artificial intelligence; Convergence; Feedforward neural networks; Jacobian matrices; Linear systems; Mathematics; Neural networks; Newton method; Nonlinear equations; Stability;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.831132

Filename

831132