Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/22279
Appears in Collections:Computing Science and Mathematics Conference Papers and Proceedings
Author(s): Swingler, Kevin
Smith, Leslie
Contact Email: l.s.smith@stir.ac.uk
Title: Mixed order associative networks for function approximation, optimisation and sampling
Citation: Swingler K & Smith L (2013) Mixed order associative networks for function approximation, optimisation and sampling. In: ESANN 2013 proceedings, 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013, Bruges, Belgium, 24.04.2013-26.04.2013. ESANN, pp. 23-28. http://www.i6doc.com/en/livre/?GCOI=28001100131010
Issue Date: Jun-2013
Date Deposited: 30-Sep-2015
Conference Name: 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013
Conference Dates: 2013-04-24 - 2013-04-26
Conference Location: Bruges, Belgium
Abstract: A mixed order associative neural network with n neurons and a modified Hebbian learning rule can learn any functionf : {-1,1}n → R  and reproduce its output as the network's energy function. The network weights are equal to Walsh coecients, the fixed point attractors are local maxima in the function, and partial sums across the weights of the network calculate averages for hyperplanes through the function. If the network is trained on data sampled from a distribution, then marginal and conditional probability calculations may be made and samples from the distribution generated from the network. These qualities make the network ideal for optimisation fitness function modelling and make the relationships amongst variables explicit in a way that architectures such as the MLP do not.
Status: VoR - Version of Record
Rights: Publisher allows this work to be made available in this repository. Published in ESANN 2013 with the following policy: You are free to download, copy and distribute this paper, provided that you keep the reference of the paper that has been added as header to each page
URL: http://www.i6doc.com/en/livre/?GCOI=28001100131010

Files in This Item:
File Description SizeFormat 
Swingler_ESANN_2013.pdfFulltext - Published Version185.12 kBAdobe PDFView/Open



This item is protected by original copyright



Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.