eCite Digital Repository

An empirically-sourced heuristic for predetermining the size of the hidden layer of a multi-layer perceptron for large datasets

Citation

Lunt, AJ and Xu, S, An empirically-sourced heuristic for predetermining the size of the hidden layer of a multi-layer perceptron for large datasets, AI 2016: Advances in Artificial Intelligence, Proceedings of the 29th Australasian Joint Conference, 5-8 December 2016, Hobart, Tasmania, pp. 542-547. ISBN 978-3-319-50126-0 (2016) [Refereed Conference Paper]

Copyright Statement

Copyright 2016 Springer International Publishing AG.

DOI: doi:10.1007/978-3-319-50127-7_47

Abstract

We recommend a guiding heuristic to locate a sufficiently-sized multilayer perceptron (MLP) for larger datasets. Expected to minimise the search scope, it is based on experimental research into the comparative performance of 14 existing approaches with global minimum ranges on 31 larger datasets. The most consistent performer was Baumís equation that sets the number of hidden neurons equal to the square root of the number of training instances.

Item Details

Item Type:Refereed Conference Paper
Keywords:neural network, multilayer perceptron, hidden layer size, global minimum, local minimum
Research Division:Information and Computing Sciences
Research Group:Artificial Intelligence and Image Processing
Research Field:Neural, Evolutionary and Fuzzy Computation
Objective Division:Information and Communication Services
Objective Group:Other Information and Communication Services
Objective Field:Information and Communication Services not elsewhere classified
Author:Lunt, AJ (Ms Amanda Lunt)
Author:Xu, S (Dr Shuxiang Xu)
ID Code:118098
Year Published:2016
Deposited By:Information and Communication Technology
Deposited On:2017-07-04
Last Modified:2017-11-18
Downloads:0

Repository Staff Only: item control page