Please use this identifier to cite or link to this item:
Appears in Collections:Computing Science and Mathematics Book Chapters and Sections
Title: Opening the Black Box: Analysing MLP Functionality Using Walsh Functions
Author(s): Swingler, Kevin
Contact Email:
Editor(s): Merelo, JJ
Rosa, A
Cadenas, JM
Dourado, A
Madani, K
Filipe, J
Citation: Swingler K (2016) Opening the Black Box: Analysing MLP Functionality Using Walsh Functions. In: Merelo J, Rosa A, Cadenas J, Dourado A, Madani K & Filipe J (eds.) Computational Intelligence. Studies in Computational Intelligence, 620. International Joint Conference on Computational Intelligence (IJCCI) 2014, Rome, Italy, 22.10.2014-24.10.2014. Cham, Switzerland: Springer, pp. 303-323.
Keywords: Black box neural network
Multilayer perceptions
Walsh functions
Network function analysis
Issue Date: 2016
Date Deposited: 18-Mar-2019
Series/Report no.: Studies in Computational Intelligence, 620
Abstract: The Multilayer Perceptron (MLP) is a neural network architecture that is widely used for regression, classification and time series forecasting. One often cited disadvantage of the MLP, however, is the difficulty associated with human understanding of a particular MLP’s function. This so called black box limitation is due to the fact that the weights of the network reveal little about structure of the function they implement. This paper proposes a method for understanding the structure of the function learned by MLPs that model functions of the class f:{−1,1}^n->R. This includes regression and classification models. A Walsh decomposition of the function implemented by a trained MLP is performed and the coefficients analysed. The advantage of a Walsh decomposition is that it explicitly separates the contribution to the function made by each subset of input neurons. It also allows networks to be compared in terms of their structure and complexity. The method is demonstrated on some small toy functions and on the larger problem of the MNIST handwritten digit classification data set.
Rights: This is a post-peer-review, pre-copyedit version of a paper published in Merelo J., Rosa A., Cadenas J., Dourado A., Madani K., Filipe J. (eds) Computational Intelligence. Studies in Computational Intelligence, vol 620. Springer, Cham. The final authenticated version is available online at:
DOI Link: 10.1007/978-3-319-26393-9_18

Files in This Item:
File Description SizeFormat 
SwinglerSCI2015.pdfFulltext - Accepted Version241.85 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

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