Analysing the behaviour of neural networks
Breutel, Stephan Werner (2004) Analysing the behaviour of neural networks. PhD thesis, Queensland University of Technology.

Stephan Breutel Thesis (PDF 1MB) 
Abstract
A new method is developed to determine a set of informative and refined interface assertions
satisfied by functions that are represented by feedforward neural networks. Neural networks have often been criticized for their low degree of comprehensibility.It is difficult to have confidence in software components if they have no clear and valid interface description. Precise and understandable interface assertions for a neural network based software component are required for safety critical applications and for theintegration into larger software systems.
The interface assertions we are considering are of the form "e if the input x of the neural
network is in a region (alpha symbol) of the input space then the output f(x) of the neural network will be in the region (beta symbol) of the output space "e and vice versa. We are interested in computing refined interface assertions, which can be viewed as the computation of the strongest pre and postconditions a feedforward neural network fulfills. Unions ofpolyhedra (polyhedra are the generalization of convex polygons in higher dimensional spaces) are well suited for describing arbitrary regions of higher dimensional vector spaces. Additionally, polyhedra are closed under affine transformations.
Given a feedforward neural network, our method produces an annotated neural network,
where each layer is annotated with a set of valid linear inequality predicates.
The main challenges for the computation of these assertions is to compute the solution
of a nonlinear optimization problem and the projection of a polyhedron onto a
lowerdimensional subspace.
Impact and interest:
Citation counts are sourced monthly from Scopus and Web of Science® citation databases.
These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.
Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.
Fulltext downloads:
Fulltext downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.
ID Code:  15943 

Item Type:  QUT Thesis (PhD) 
Supervisor:  Maire, Frederic & Hayward, Ross 
Keywords:  artificial neural network, annotated artificial neural netwrok, ruleextraction, validation of neural network, polyhedra, forwardpropagation, backwardpropagation, refinement process, nonlinear optimization, polyhedral computation, polyhedral projection techniques. 
Divisions:  Past > QUT Faculties & Divisions > Faculty of Science and Technology 
Department:  Faculty of Information Technology 
Institution:  Queensland University of Technology 
Copyright Owner:  Copyright Stephan Werner Breutel 
Deposited On:  03 Dec 2008 03:53 
Last Modified:  28 Oct 2011 19:41 
Export: EndNote  Dublin Core  BibTeX
Repository Staff Only: item control page