Bounds for the average generalization error of the mixture of experts neural network

• Type: Article in International Scientific Journal
• Date: 2004

Authors

Luis Alexandre (Author) FEUP; Aurélio Campilho (Author) FEUP

Journal

The Journal is awaiting validation by the Administrative Services.

Title: INTERACTIVE SYSTEMS: DESIGN, SPECIFICATION, AND VERIFICATION

Vol. 3138

Pages: 618-625

Indexing

ISI Proceedings

ISI Web of Knowledge - 4 Citations

ISI Web of Science

Scopus - 5 Citations

Scientific classification

FOS: Engineering and technology

CORDIS: Technological sciences > Engineering > Electronic engineering

Other information

Authenticus ID: P-000-DPP

DOI: 10.1007/978-3-540-27868-9_67

Abstract (EN): In this paper we derive an upper bound for the average-case generalization error of the mixture of experts modular neural network, based on an average-case generalization error bound for an isolated neural network. By doing this we also generalize a previous bound for this architecture that was restricted to special problems. We also present a correction factor for the original average generalization error, that was empirically obtained, that yields more accurate error bounds for the 6 data sets used in the experiments. These experiments illustrate the validity of the derived error bound for the mixture of experts modular neural network and show how it can be used in practice.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 8