On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs

Mehul Rastogi, Sen Lu, Nafiul Islam, Abhronil Sengupta

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

Neuromorphic computing is emerging to be a disruptive computational paradigm that attempts to emulate various facets of the underlying structure and functionalities of the brain in the algorithm and hardware design of next-generation machine learning platforms. This work goes beyond the focus of current neuromorphic computing architectures on computational models for neuron and synapse to examine other computational units of the biological brain that might contribute to cognition and especially self-repair. We draw inspiration and insights from computational neuroscience regarding functionalities of glial cells and explore their role in the fault-tolerant capacity of Spiking Neural Networks (SNNs) trained in an unsupervised fashion using Spike-Timing Dependent Plasticity (STDP). We characterize the degree of self-repair that can be enabled in such networks with varying degree of faults ranging from 50 to 90% and evaluate our proposal on the MNIST and Fashion-MNIST datasets.

Original languageEnglish (US)
Article number603796
JournalFrontiers in Neuroscience
Volume14
DOIs
StatePublished - Jan 14 2021

All Science Journal Classification (ASJC) codes

  • General Neuroscience

Fingerprint

Dive into the research topics of 'On the Self-Repair Role of Astrocytes in STDP Enabled Unsupervised SNNs'. Together they form a unique fingerprint.

Cite this