research-article

Formal Validation of Neural Networks as Timed Automata

Authors:

Elisabetta De Maria,

Cinzia Di Giusto,

Giovanni CiattoAuthors Info & Claims

CSBio '17: Proceedings of the 8th International Conference on Computational Systems-Biology and Bioinformatics

Pages 15 - 22

https://doi.org/10.1145/3156346.3156350

Published: 07 December 2017 Publication History

Abstract

We propose a formalisation of spiking neural networks based on timed automata networks. Neurons are modelled as timed automata waiting for inputs on a number of different channels (synapses), for a given amount of time (the accumulation period). When this period is over, the current potential value is computed taking into account the current inputs and the previous decayed potential value. If the current potential overcomes a given threshold, the automaton emits a broadcast signal over its output channel, otherwise it restarts another accumulation period. After each emission, the automaton is constrained to remain inactive for a fixed refractory period. Spiking neural networks are formalised as sets of automata, one for each neuron, running in parallel and sharing channels according to the structure of the network. The model is then validated against some crucial properties defined via proper temporal logic formulae.

References

[1]

Rajeev Alur and David L. Dill. 1994. A Theory of Timed Automata. Theor. Comput. Sci. 126, 2 (April 1994), 183--235.

Digital Library

[2]

Bogdan Aman and Gabriel Ciobanu. 2016. Modelling and verification of weighted spiking neural systems. Theoretical Computer Science 623 (2016), 92--102.

Digital Library

[3]

Johan Bengtsson, Kim G. Larsen, Fredrik Larsson, Paul Pettersson, and Wang Yi. 1995. Uppaal --- a Tool Suite for Automatic Verification of Real--Time Systems. In Proceedings of Workshop on Verification and Control of Hybrid Systems III (Lecture Notes in Computer Science). Springer--Verlag, 232--243.

Digital Library

[4]

Giovanni Ciatto, Elisabetta De Maria, and Cinzia Di Giusto. 2016. Additional material. https://github.com/gciatto/snn_as_ta. (2016).

[5]

Giovanni Ciatto, Elisabetta De Maria, and Cinzia Di Giusto. 2017. Spiking Neural Networks as Timed Automata. In Proceedings of Advances in Systems and Synthetic Biology. 55--68.

[6]

Edmund M. Clarke, Jr., Orna Grumberg, and Doron A. Peled. 1999. Model checking. MIT Press, Cambridge, MA, USA.

Digital Library

[7]

G. Cybenko. 1989. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems 2, 4 (1989), 303--314.

[8]

Elisabetta De Maria, Alexandre Muzy, Daniel Gaffé, Annie Ressouche, and Franck Grammont. 2016. Verification of Temporal Properties of Neuronal Archetypes Using Synchronous Models. In Fifth International Workshop on Hybrid Systems Biology. Grenoble, France.

[9]

G. B. Ermentrout and N. Kopell. 1986. Parabolic Bursting in an Excitable System Coupled with a Slow Oscillation. SIAM J. Appl. Math. 46, 2 (1986), 233--253.

Digital Library

[10]

Yoav Freund and Robert E. Schapire. 1999. Large Margin Classification Using the Perceptron Algorithm. Machine Learning 37, 3 (1999), 277--296.

Digital Library

[11]

A. L. Hodgkin and A. F. Huxley. 1952. A quantitative description of membrane current and its application to conduction and excitation in nerve. The Journal of Physiology 117, 4 (1952), 500--544.

[12]

E. M. Izhikevich. 2003. Simple Model of Spiking Neurons. Trans. Neur. Netw. 14, 6 (2003), 1569--1572.

Digital Library

[13]

E. M. Izhikevich. 2004. Which model to use for cortical spiking neurons? IEEE Transactions on Neural Networks 15, 5 (2004), 1063--1070.

Digital Library

[14]

L. Lapicque. 1907. Recherches quantitatives sur l'excitation electrique des nerfs traitee comme une polarization. J Physiol Pathol Gen 9 (1907), 620--635.

[15]

Wolfgang Maass. 1997. Networks of spiking neurons: The third generation of neural network models. Neural Networks 10, 9 (1997), 1659--1671.

[16]

Warren S. McCulloch and Walter Pitts. 1943. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics 5, 4 (1943), 115--133.

[17]

Hélène Paugam-Moisy and Sander Bohte. 2012. Computing with Spiking Neuron Networks. Springer Berlin Heidelberg, Berlin, Heidelberg, 335--376.

Cited By

Leugering J(2024)TickTockTokens: a minimal building block for event-driven systems2024 Neuro Inspired Computational Elements Conference (NICE)10.1109/NICE61972.2024.10549408(1-8)Online publication date: 23-Apr-2024
https://doi.org/10.1109/NICE61972.2024.10549408
Leugering J(2022)Modeling and analyzing neuromorphic SNNs as discrete event systemsProceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference10.1145/3517343.3517362(61-62)Online publication date: 28-Mar-2022
https://dl.acm.org/doi/10.1145/3517343.3517362
Huang SDiep MJang KCherry EFenton FCleaveland RLindvall MMangharam RPorter A(2020)Towards Automated Comprehension and Alignment of Cardiac Models at the System Invariant LevelCSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics10.1145/3429210.3429225(18-28)Online publication date: 19-Nov-2020
https://dl.acm.org/doi/10.1145/3429210.3429225
Show More Cited By

Index Terms

Formal Validation of Neural Networks as Timed Automata

Recommendations

Interrupt Timed Automata: verification and expressiveness

We introduce the class of Interrupt Timed Automata (ITA), a subclass of hybrid automata well suited to the description of timed multi-task systems with interruptions in a single processor environment.

While the reachability problem is undecidable for ...
Past pushdown timed automata and safety verification
Implementation and application automata

We consider past pushdown timed automata that are discrete pushdown timed automata with past formulas as enabling conditions. Using past formulas allows a past pushdown timed automaton to access the past values of the finite state variables in the ...
Presburger liveness verification of discrete timed automata

Using an automata-theoretic approach, we investigate the decidability of liveness properties (called Presburger liveness properties) for timed automata when Presburger formulas on configurations are allowed. While the general problem of checking a ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

CSBio '17: Proceedings of the 8th International Conference on Computational Systems-Biology and Bioinformatics

December 2017

83 pages

ISBN:9781450353502

DOI:10.1145/3156346

Copyright © 2017 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

In-Cooperation

SOICT: School of Information and Communication Technology - HUST
NAFOSTED: The National Foundation for Science and Technology Development
KMUTT: King Mongkut's University of Technology Thonburi

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 December 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

CSBio '17

CSBio '17: 8th International Conference on Computational Systems-Biology and Bioinformatics

December 7 - 8, 2017

Nha Trang City, Viet Nam

Acceptance Rates

Overall Acceptance Rate 23 of 37 submissions, 62%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
88
Total Downloads

Downloads (Last 12 months)4
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Leugering J(2024)TickTockTokens: a minimal building block for event-driven systems2024 Neuro Inspired Computational Elements Conference (NICE)10.1109/NICE61972.2024.10549408(1-8)Online publication date: 23-Apr-2024
https://doi.org/10.1109/NICE61972.2024.10549408
Leugering J(2022)Modeling and analyzing neuromorphic SNNs as discrete event systemsProceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference10.1145/3517343.3517362(61-62)Online publication date: 28-Mar-2022
https://dl.acm.org/doi/10.1145/3517343.3517362
Huang SDiep MJang KCherry EFenton FCleaveland RLindvall MMangharam RPorter A(2020)Towards Automated Comprehension and Alignment of Cardiac Models at the System Invariant LevelCSBio '20: Proceedings of the Eleventh International Conference on Computational Systems-Biology and Bioinformatics10.1145/3429210.3429225(18-28)Online publication date: 19-Nov-2020
https://dl.acm.org/doi/10.1145/3429210.3429225
De Maria EDi Giusto CLaversa L(2019)Spiking neural networks modelled as timed automata: with parameter learningNatural Computing10.1007/s11047-019-09727-9Online publication date: 17-Jan-2019
https://doi.org/10.1007/s11047-019-09727-9

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten