Accelerated physical emulation of Bayesian inference in spiking neural networks

TL;DR

This paper demonstrates a robust, accelerated spiking neural network model performing Bayesian inference on a neuromorphic platform, highlighting advantages of brain-inspired physical computation for generative and discriminative tasks.

Contribution

It introduces a novel spiking network model for Bayesian inference that operates effectively on neuromorphic hardware, showcasing robustness and accelerated computation.

Findings

Successful implementation of Bayesian inference via sampling on BrainScaleS platform

Robustness to analog substrate imperfections demonstrated

Accelerated computation compared to traditional methods

Abstract

The massively parallel nature of biological information processing plays an important role for its superiority to human-engineered computing devices. In particular, it may hold the key to overcoming the von Neumann bottleneck that limits contemporary computer architectures. Physical-model neuromorphic devices seek to replicate not only this inherent parallelism, but also aspects of its microscopic dynamics in analog circuits emulating neurons and synapses. However, these machines require network models that are not only adept at solving particular tasks, but that can also cope with the inherent imperfections of analog substrates. We present a spiking network model that performs Bayesian inference through sampling on the BrainScaleS neuromorphic platform, where we use it for generative and discriminative computations on visual data. By illustrating its functionality on this platform, we implicitly demonstrate its robustness to various substrate-specific distortive effects, as well as its accelerated capability for computation. These results showcase the advantages of brain-inspired physical computation and provide important building blocks for large-scale neuromorphic applications.