• Home
  • Search
  • A Compositional Framework for Neural Network Modeling Using Typed Petri Nets
  • https://doi.org/10.1527/tjsai.41-2_fn26-iCopy DOI Icon

A Compositional Framework for Neural Network Modeling Using Typed Petri Nets

  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

The increasing complexity of modern neural networks impedes systematic understanding and formal analysis,often resulting in “black box” behavior. Our paper introduces Typed Petri Nets (TPNs) as a formal framework formodeling the structure and dynamics of neural networks, aiming to address these challenges. We define the corecomponents of TPNs―places, transitions, arcs, a type system (e.g., for tensors), and computation assignments―anddemonstrate how they can compositionally represent basic network layers. Furthermore, we illustrate the capability ofTPNs to model advanced architectures, including convolutional layers, skip connections, and multi-branch structures.TPN dynamics naturally simulate forward propagation through markings and firing rules. The framework’sformal semantics can be rigorously explored using category theory, as illustrated by applications in probabilistic contextsusing Markov Categories. Key advantages of the TPN approach include modularity through compositionality,explicit information flow representation, type safety, and a foundation for formal analysis. This work establishesTPN as a structured, mathematically grounded perspective for understanding complex neural networks, offering apromising basis for future research into learning dynamics, verification, and tool development.

Similar Papers
  • Research Article

Analysis of the geometric structure of neural networks and neural ODEs via morse functions

  • Feb 01, 2026
  • Advances in Computational Mathematics
  • Christian Kuehn +1
  • Research Article
  • Citations41

Nonlinear systems identification and control via dynamic multitime scales neural networks.

  • Nov 01, 2013
  • IEEE transactions on neural networks and learning systems
  • Zhi-Jun Fu +3
  • PDF
  • Addendum
  • Citations12

Correction: Network Evolution Induced by Asynchronous Stimuli through Spike-Timing-Dependent Plasticity

  • Jan 29, 2014
  • PLoS ONE
  • Wu-Jie Yuan +2
  • PDF
  • Research Article
  • Citations1

Ranking of Search Requests in the Digital Information Retrieval System Based on Dynamic Neural Networks

  • Jan 01, 2022
  • Complexity
  • Viera Bartosova +4
  • Conference Article
  • Citations9

Reinforcement learning method for continuous state space based on dynamic neural network

  • Jan 01, 2008
  • Wei Sun +2
  • Conference Article

Structure-Based Testing Criteria and Testing Case Generation for Deep Learning Systems

  • Jan 01, 2025
  • Yining Chen
  • Conference Article
  • Citations6

<title>Dynamic neural network for visual memory</title>

  • Sep 01, 1990
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Madan M Gupta +1
  • Book Chapter

Finite Impulse Response Neural Networks with Applications in Speed Control of DC Motor Drive

  • Jan 01, 2009
  • A. S. Sallam +1
  • Supplementary Content
  • Citations1

Interpretable machine learning for additive manufacturing

  • Jun 10, 2019
  • Figshare
  • Raquel Conceição Ferreira
  • Research Article
  • Citations7

Equation-based domain knowledge utilization into neural network structure and learning

  • Jun 12, 2018
  • Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering
  • Shrinivas Kulkarni +1
  • Research Article
  • Citations7

Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization

  • Feb 01, 2025
  • IEEE Transactions on Consumer Electronics
  • Chunjiong Zhang +3
  • Research Article

Abstract C006: DrugCell: A visible neural network to guide precision medicine

  • Dec 01, 2019
  • Molecular Cancer Therapeutics
  • Brent M Kuenzi +4
  • Supplementary Content

Co-Contextual Type Systems: Contextless Deductive Reasoning for Correct Incremental Type Checking

  • Mar 02, 2020
  • TUbilio (Technical University of Darmstadt)
  • Edlira Kuci
  • Research Article

INTELLIGENT MODEL FOR CLASSIFYING HEMODYNAMIC PATTERNS OF BRAIN ACTIVATION TO IDENTIFY NEUROCOGNITIVE MECHANISMS OF SPATIAL-NUMERICAL ASSOCIATIONS

  • Jan 01, 2024
  • Vestnik komp'iuternykh i informatsionnykh tekhnologii
  • R G Asadullaev +1
  • Dissertation

Optimizing neural network structures

  • Nov 19, 2018
  • Zhe Li
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.