Learning flow functions of spiking systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Aguiar, Miguel, Das, Amritam, Johansson, Karl H.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929408677249024
author Aguiar, Miguel
Das, Amritam
Johansson, Karl H.
author_facet Aguiar, Miguel
Das, Amritam
Johansson, Karl H.
contents We propose a framework for surrogate modelling of spiking systems. These systems are often described by stiff differential equations with high-amplitude oscillations and multi-timescale dynamics, making surrogate models an attractive tool for system design and simulation. We parameterise the flow function of a spiking system using a recurrent neural network architecture, allowing for a direct continuous-time representation of the state trajectories. The spiking nature of the signals makes for a data-heavy and computationally hard training process; thus, we describe two methods to mitigate these difficulties. We demonstrate our framework on two conductance-based models of biological neurons, showing that we are able to train surrogate models which accurately replicate the spiking behaviour.
format Preprint
id arxiv_https___arxiv_org_abs_2312_11913
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning flow functions of spiking systems
Aguiar, Miguel
Das, Amritam
Johansson, Karl H.
Systems and Control
We propose a framework for surrogate modelling of spiking systems. These systems are often described by stiff differential equations with high-amplitude oscillations and multi-timescale dynamics, making surrogate models an attractive tool for system design and simulation. We parameterise the flow function of a spiking system using a recurrent neural network architecture, allowing for a direct continuous-time representation of the state trajectories. The spiking nature of the signals makes for a data-heavy and computationally hard training process; thus, we describe two methods to mitigate these difficulties. We demonstrate our framework on two conductance-based models of biological neurons, showing that we are able to train surrogate models which accurately replicate the spiking behaviour.
title Learning flow functions of spiking systems
topic Systems and Control
url https://arxiv.org/abs/2312.11913