Astromorphic Self-Repair of Neuromorphic Hardware Systems

TL;DR

This paper introduces bio-inspired astrocyte models for self-repair in neuromorphic hardware, demonstrating improved fault tolerance and learning accuracy in SNN systems on standard datasets.

Contribution

It develops macro-models of astrocytes with high bio-fidelity and integrates them into neuromorphic systems for self-repair of hardware faults.

Findings

Bio-morphic astrocytic regulation improves fault repair accuracy.

Enhanced repair convergence in neuromorphic hardware.

Effective self-repair in unsupervised learning tasks on MNIST datasets.

Abstract

While neuromorphic computing architectures based on Spiking Neural Networks (SNNs) are increasingly gaining interest as a pathway toward bio-plausible machine learning, attention is still focused on computational units like the neuron and synapse. Shifting from this neuro-synaptic perspective, this paper attempts to explore the self-repair role of glial cells, in particular, astrocytes. The work investigates stronger correlations with astrocyte computational neuroscience models to develop macro-models with a higher degree of bio-fidelity that accurately captures the dynamic behavior of the self-repair process. Hardware-software co-design analysis reveals that bio-morphic astrocytic regulation has the potential to self-repair hardware realistic faults in neuromorphic hardware systems with significantly better accuracy and repair convergence for unsupervised learning tasks on the MNIST and F-MNIST datasets. Our implementation source code and trained models are available at https://github.com/NeuroCompLab-psu/Astromorphic_Self_Repair.