Skip navigation
Skip navigation

The Effect of Bottlenecks on Generalisation in Backpropagation Neural Networks

Zang, Xu

Description

Many modifications have been proposed to improve back-propagation's convergence time and generalisation capabilities. Typical techniques involve pruning of hidden neurons, adding noise to hidden neurons which do not learn, and reducing dataset size. In this paper, we wanted to compare these modifications' performance in many situations, perhaps for which they were not designed. Seven famous UCI datasets were used. These datasets are different in dimension, size and number of outliers. After...[Show more]

CollectionsANU Research Publications
Date published: 2010
Type: Conference paper
URI: http://hdl.handle.net/1885/55175
Source: Proceedings of the International Conference on Neural Information Processing (ICONIP 2010)
DOI: 10.1007/978-3-642-17534-3_21

Download

File Description SizeFormat Image
01_Zang_The_Effect_of_Bottlenecks_on_2010.pdf370.53 kBAdobe PDF    Request a copy


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

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator