Skip navigation
Skip navigation

Generalisation Performance vs. Architecture Variations in Constructive Cascade Networks

Khoo, Sui; Gedeon, Tamas (Tom)

Description

Constructive cascade algorithms are powerful methods for training feedforward neural networks with automation of the task of specifying the size and topology of network to use. A series of empirical studies were performed to examine the effect of imposing constraints on constructive cascade neural network architectures. Building a priori knowledge of the task into the network gives better generalisation performance. We introduce our Local Feature Constructive Cascade (LoCC) and Symmetry Local...[Show more]

CollectionsANU Research Publications
Date published: 2009
Type: Book chapter
URI: http://hdl.handle.net/1885/52318
DOI: 10.1007/978-3-642-03040-6_29

Download

File Description SizeFormat Image
01_Khoo_Generalisation_Performance_vs._2009.pdf184.83 kBAdobe PDF    Request a copy
02_Khoo_Generalisation_Performance_vs._2009.pdf173.26 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  23 August 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator