Monitoring of MTL specifications with IBM's spiking-neuron model

This paper shows how to use the IBM's TrueNorth spiking neuron model, for monitoring if a digital signal satisfies a metric temporal-logic (MTL) specification. TrueNorth spiking neurons are universal computation blocks, which can perform a variety of deterministic or stochastic tasks (e.g., Boolean/arithmetic operations, filtering, and convolution) depending on the configuration of their parameters. We show how to set these parameters for the deterministic TrueNorth neural-model in order to recognize MTL operators. A TrueNorth circuit then behaves as a runtime MTL monitor. We demonstrate how to translate the neural monitor to synthesizable HDL-code on Xilinx's Zedboard using high-level synthesis. To the best of our knowledge, this is the first application of the IBM's TrueNorth model for runtime monitoring. It also demonstrates the complete flow from a high-level specification to the implementation of a neural monitor in FPGA. As a byproduct, the paper also introduces the first open-source FPGA implementation of the deterministic TrueNorth model. We demonstrate the usefulness of our approach on a case study, the launching of a missile from a battle ship.

[1]  Mark Weiser,et al.  Source Code , 1987, Computer.

[2]  Zohar Manna,et al.  The Temporal Logic of Reactive and Concurrent Systems , 1991, Springer New York.

[3]  Thomas A. Henzinger,et al.  Real-Time Logics: Complexity and Expressiveness , 1993, Inf. Comput..

[4]  Robert J. Vanderbei,et al.  Linear Programming: Foundations and Extensions , 1998, Kluwer international series in operations research and management service.

[5]  Daniel Geist,et al.  Combining system level modeling with assertion based verification , 2005, Sixth international symposium on quality electronic design (isqed'05).

[6]  D. Borrione,et al.  On-line assertion-based verification with proven correct monitors , 2005, 2005 International Conference on Information and Communication Technology.

[7]  Dejan Nickovic,et al.  From MITL to Timed Automata , 2006, FORMATS.

[8]  Dejan Nickovic,et al.  On Synthesizing Controllers from Bounded-Response Properties , 2007, CAV.

[9]  Joël Ouaknine,et al.  Some Recent Results in Metric Temporal Logic , 2008, FORMATS.

[10]  Amir Pnueli,et al.  On the Merits of Temporal Testers , 2008, 25 Years of Model Checking.

[11]  C. Watterson,et al.  A runtime verification monitoring approach for embedded industrial controllers , 2008, 2008 IEEE International Symposium on Industrial Electronics.

[12]  Marco Roveri,et al.  Formalization and Validation of Safety-Critical Requirements , 2009, FMA.

[13]  Martin Leucker,et al.  Teaching Runtime Verification , 2011, RV.

[14]  Ezio Bartocci,et al.  Runtime Verification with State Estimation , 2011, RV.

[15]  Dejan Nickovic,et al.  Monitoring properties of analog and mixed-signal circuits , 2012, International Journal on Software Tools for Technology Transfer.

[16]  Andrew S. Cassidy,et al.  Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[17]  Baruch Sterin,et al.  A circuit approach to LTL model checking , 2013, 2013 Formal Methods in Computer-Aided Design.

[18]  Andrew S. Cassidy,et al.  Cognitive computing systems: Algorithms and applications for networks of neurosynaptic cores , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[19]  S. Stoller,et al.  Runtime Verification with Particle Filtering , 2013, RV.

[20]  Andrew S. Cassidy,et al.  Cognitive computing programming paradigm: A Corelet Language for composing networks of neurosynaptic cores , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[21]  Matthias Függer,et al.  Runtime verification of embedded real-time systems , 2014, Formal Methods Syst. Des..

[22]  Wulfram Gerstner,et al.  Neuronal Dynamics: From Single Neurons To Networks And Models Of Cognition , 2014 .

[23]  Dejan Nickovic,et al.  From signal temporal logic to FPGA monitors , 2015, 2015 ACM/IEEE International Conference on Formal Methods and Models for Codesign (MEMOCODE).