Probabilistic Modeling of Spiking Neural Networks with Contract-Based Verification

2025-06-16

AI Summary

This study addresses the challenge of ensuring global temporal reliability for Spiking Neural Network (SNN) composite models under stochastic timing uncertainties. Methodologically, we propose the first verification framework for SNNs that integrates formal contracts with probabilistic modeling: (i) we develop parameterized neuron-bundle and synapse models supporting both temporal and probabilistic semantics; (ii) we introduce a temporal-logic–based assume-guarantee contract language to specify global stochastic response constraints; and (iii) we combine model checking with discrete-event simulation for rigorous verification. Key contributions include: (i) the first systematic application of formal contract-based verification to SNN modeling, unifying neuron-level delay and probabilistic modeling with system-level temporal reliability guarantees; and (ii) a lightweight, toolchain-compatible framework—compilable to mainstream verification tools—that enables formal verification for medium-scale SNNs and statistical testing for large-scale models.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Spiking Neural Networks (SNN) are models for"realistic"neuronal computation, which makes them somehow different in scope from"ordinary"deep-learning models widely used in AI platforms nowadays. SNNs focus on timed latency (and possibly probability) of neuronal reactive activation/response, more than numerical computation of filters. So, an SNN model must provide modeling constructs for elementary neural bundles and then for synaptic connections to assemble them into compound data flow network patterns. These elements are to be parametric patterns, with latency and probability values instantiated on particular instances (while supposedly constant"at runtime"). Designers could also use different values to represent"tired"neurons, or ones impaired by external drugs, for instance. One important challenge in such modeling is to study how compound models could meet global reaction requirements (in stochastic timing challenges), provided similar provisions on individual neural bundles. A temporal language of logic to express such assume/guarantee contracts is thus needed. This may lead to formal verification on medium-sized models and testing observations on large ones. In the current article, we make preliminary progress at providing a simple model framework to express both elementary SNN neural bundles and their connecting constructs, which translates readily into both a model-checker and a simulator (both already existing and robust) to conduct experiments.

Problem

• Modeling probabilistic spiking neural networks with contracts
• Verifying global reaction requirements in SNNs
• Translating SNN models into verifiable and simulatable frameworks

Innovation

• Parametric SNN modeling with latency and probability
• Temporal logic for assume/guarantee contract verification
• Framework translating to model-checker and simulator