Learning flow functions of spiking systems

2023/12/19 by Aguiar, Miguel, Das, Amritam, Johansson, Karl H.
#FOS: Electrical engineering #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2312.11913

Abstract

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.

Related

• Using Firing-Rate Dynamics to Train Recurrent Networks of Spiking Model Neurons
• Surrogate Gradient Learning in Spiking Neural Networks
• An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
• Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neural Networks
• Spiking Neural Networks: a theoretical framework for Universal Approximation and training