A Heterogeneous General Model for Neuromorphic-Inspired Computation
Abstract
In recent years, both academia and industry have focused on the development of computational architectures inspired by the distributed, adaptive, and event-driven characteristics of biological neural systems, with the aim of reducing the computational cost associated with conventional training approaches [1]. However, a major challenge is the lack of general models and design guidelines for emerging computational systems and hardware. This work introduces a general model based on an input-dependent stochastic weight network, referred to as a substrate. The substrate weights evolve through input-triggered stochastic updates, with correlations between weight coefficients described by a matrix-valued covariance kernel. The proposed framework is implemented using quadratic polynomial weight functions, where the input amplitude controls the magnitude of the stochastic perturbation and a substrate-dependent distance determines the correlation structure. Numerical simulations show that correlations in the stochastic weight evolution significantly affect the system response, suggesting a potential mechanism for neuromorphic-inspired computation without conventional weight training. The aim of this work is to provide a general formulation of the model and identify its main properties and characteristics. 1 H. Jaeger, Towards a generalized theory comprising digital, neuromorphic and unconventional computing, Neuromorphic Comput. Eng., vol. 1, no. 1, p. 012002, Sep. 2021
Related
- Local information processing capacity: anatomy of computation in neuromorphic systems
- Controlling Switching Evolution in Lead-Free Perovskite-Inspired Chalcogenide Memristors for Neuromorphic Computing
- Quantum Networking at the Speed of Quantum Computation: Kilohertz Entanglement in a Heterogeneous Quantum System
- From Syndromes to Computation: A General Framework for Logical Operations in Quantum Error-Correcting Codes
- Assessing the Transferability of General-Purpose MachineLearning Interatomic Potentials for Heterogeneous Catalysis with HetCat26
BibTeX
@misc{mirigliano2026heterogeneous,
title = {{A Heterogeneous General Model for Neuromorphic-Inspired Computation}},
author = {Matteo Mirigliano},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.05482},
eprint = {2609.05482},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.05482},
}
RIS
TY - UNPB
TI - A Heterogeneous General Model for Neuromorphic-Inspired Computation
AU - Matteo Mirigliano
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.05482
UR - https://arxiv.org/abs/2609.05482
AB - In recent years, both academia and industry have focused on the development of computational architectures inspired by the distributed, adaptive, and event-driven characteristics of biological neural systems, with the aim of reducing the computational cost associated with conventional training approaches [1]. However, a major challenge is the lack of general models and design guidelines for emerging computational systems and hardware. This work introduces a general model based on an input-dependent stochastic weight network, referred to as a substrate. The substrate weights evolve through input-triggered stochastic updates, with correlations between weight coefficients described by a matrix-valued covariance kernel. The proposed framework is implemented using quadratic polynomial weight functions, where the input amplitude controls the magnitude of the stochastic perturbation and a substrate-dependent distance determines the correlation structure. Numerical simulations show that correlations in the stochastic weight evolution significantly affect the system response, suggesting a potential mechanism for neuromorphic-inspired computation without conventional weight training. The aim of this work is to provide a general formulation of the model and identify its main properties and characteristics. 1 H. Jaeger, Towards a generalized theory comprising digital, neuromorphic and unconventional computing, Neuromorphic Comput. Eng., vol. 1, no. 1, p. 012002, Sep. 2021
ER -