Symbolic Encoding of Neural Networks using Communicating Automata with Applications to Verification of Neural Network Based Controllers

Su, Li and Bowman, H. and Wyble, Brad (2005) Symbolic Encoding of Neural Networks using Communicating Automata with Applications to Verification of Neural Network Based Controllers. In: Nineteenth International Joint Conference on Artificial Intelligence, 30 July - 5 August 2005, Edinburgh, Scotland. (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)
Official URL
http://www.ijcai.org/search.php

Abstract

This paper illustrates a way for applying formal methods techniques to specifying and verifying neural networks, with applications in the area of neural network based controllers. Formal methods have some of the characteristics of symbolic models. We describe a communicating automata [Bowman and Gomez, 2005] model of neural networks, where the standard Backpropagation (BP) algorithm [Rumelhart et al., 1986] is applied. Then we undertake a verification of this model using the model checker Uppaal [Behrmann et al., 2004], in order to predict the performance of the learning process. We discuss broad issues of integrating symbolic techniques with complex neural systems. We also argue that symbolic verifications may give theoretically well-founded ways to evaluate and justify neural learning systems.

Item Type: Conference or workshop item (Paper)
Additional information: Position paper
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming,
Divisions: Faculties > Science Technology and Medical Studies > School of Computing > Computational Intelligence Group
Depositing User: Mark Wheadon
Date Deposited: 24 Nov 2008 18:03
Last Modified: 20 Apr 2012 11:32
Resource URI: http://kar.kent.ac.uk/id/eprint/14284 (The current URI for this page, for reference purposes)
  • Depositors only (login required):