Cascade network architectures

Author

Littmann, E. ; Ritter, H.

Author_Institution

Dept. of Inf. Sci., Bielefeld Univ., Germany

Volume

2

fYear

1992

fDate

7-11 Jun 1992

Firstpage

398

Abstract

A novel incremental cascade network architecture based on error minimization is presented. The properties of this and related cascade architectures are discussed, and the influence of the objective function is investigated. The performance of the network is achieved by several layers of nonlinear units that are trained in a strictly feedforward manner and one after the other. Nonlinearity is generated by using sigmoid units and, optionally, additional powers of their activity values. Extensive benchmarking results for the XOR problem are reported, as are various classification tasks, and time series prediction. These are compared to other results reported in the literature. Direct cascading is proposed as promising approach to introducing context information in the approximation process

Keywords

feedforward neural nets; learning (artificial intelligence); XOR problem; benchmarking; error minimization; feedforward manner; incremental cascade network architecture; neural nets; nonlinear units; nonlinearity; objective function; performance; sigmoid units; time series prediction; Backpropagation algorithms; Convergence; Feedforward systems; Information science; Minimization methods; Power generation;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1992. IJCNN., International Joint Conference on

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-0559-0

Type

conf

DOI

10.1109/IJCNN.1992.226955

Filename

226955