Su, Li and Bowman, Howard and Wyble, Brad (2006) Formal Modeling of Connectionism using Concurrency Theory, an Approach Based on Automata and Model Checking. Technical report. UKC (KAR id:14514)
PDF
Language: English |
|
Download this file (PDF/951kB) |
Preview |
Request a format suitable for use with assistive technology e.g. a screenreader |
Abstract
This paper illustrates a framework for applying formal methods techniques, which are symbolic in nature, to specifying and verifying neural networks, which are sub-symbolic in nature. The paper describes a communicating automata [Bowman & Gomez, 2006] model of neural networks. We also implement the model using timed automata [Alur & Dill, 1994] and then undertake a verification of these models using the model checker Uppaal [Pettersson, 2000] in order to evaluate the performance of learning algorithms. This paper also presents discussion of a number of broad issues concerning cognitive neuroscience and the debate as to whether symbolic processing or connectionism is a suitable representation of cognitive systems. Additionally, the issue of integrating symbolic techniques, such as formal methods, with complex neural networks is discussed. We then argue that symbolic verifications may give theoretically well-founded ways to evaluate and justify neural learning systems in the field of both theoretical research and real world applications.
Item Type: | Reports and Papers (Technical report) |
---|---|
Uncontrolled keywords: | formal methods, communicating automata, timed automata, model checking, symbolic, sub-symbolic, neural networks, cognition, learning |
Subjects: | Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing |
Depositing User: | Mark Wheadon |
Date Deposited: | 24 Nov 2008 18:04 UTC |
Last Modified: | 05 Nov 2024 09:49 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/14514 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):