Amortized Inference of Neuron Parameters on Analog Neuromorphic Hardware

2026-02-11

AI Summary

This work addresses the multi-parameter calibration problem of adaptive exponential integrate-and-fire neuron models on neuromorphic hardware (BrainScaleS-2) by proposing an amortized simulation-based inference approach. By jointly training a summary network and a neural density estimator, and incorporating a binary classification constraint to filter valid parameter configurations, the method efficiently approximates the posterior distribution over seven key parameters. This study presents the first application of amortized simulation-based inference to neuromorphic hardware calibration, overcoming limitations of handcrafted features. The resulting posterior predictive samples accurately reproduce subthreshold membrane potential dynamics and generate spiking behaviors that closely match target electrophysiological observations, even under hardware-induced biases and incomplete calibration, thereby demonstrating the method’s effectiveness and robustness in complex neuron modeling.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• neuromorphic hardware
• parameter inference
• adaptive exponential integrate-and-fire
• simulation-based inference
• posterior estimation

Innovation

• amortized inference
• neuromorphic hardware
• simulation-based inference
• neural density estimation
• adaptive exponential integrate-and-fire