Amortized Inference of Neuron Parameters on Analog Neuromorphic Hardware

TL;DR

This paper demonstrates the use of amortized simulation-based inference to efficiently estimate neuron parameters in analog neuromorphic hardware, improving posterior accuracy and dynamics modeling.

Contribution

It introduces a neural density estimator with a summary network that enhances posterior focus and dynamic accuracy for neuron parameter inference.

Findings

Summary network improves posterior focus and dynamics modeling.

Posterior predictive traces closely match target observations.

Method validates amortized inference for analog neuron circuit parameterization.

Abstract

Our work utilized a non-sequential simulation-based inference algorithm to provide an amortized neural density estimator, which approximates the posterior distribution for seven parameters of the adaptive exponential integrate-and-fire neuron model of the analog neuromorphic BrainScaleS-2 substrate. We constrained the large parameter space by training a binary classifier to predict parameter combinations yielding observations in regimes of interest, i.e. moderate spike counts. We compared two neural density estimators: one using handcrafted summary statistics and one using a summary network trained in combination with the neural density estimator. The summary network yielded a more focused posterior and generated posterior predictive traces that accurately captured the membrane potential dynamics. When using handcrafted summary statistics, posterior predictive traces match the included features but show deviations in the exact dynamics. The posteriors showed signs of bias and miscalibration but were still able to yield posterior predictive samples that were close to the target observations on which the posteriors were constrained. Our results validate amortized simulation-based inference as a tool for parameterizing analog neuron circuits.