Bayesian continual learning via spiking neural networks

Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Among the main features of biological intelligence are energy efficiency, capacity for continual adaptation, and risk management via uncertainty quantification. Neuromorphic engineering has been thus far mostly driven by the goal of implementing energy-efficient machines that take inspiration from the time-based computing paradigm of biological brains. In this paper, we take steps toward the design of neuromorphic systems that are capable of adaptation to changing learning tasks, while producing well-calibrated uncertainty quantification estimates. To this end, we derive online learning rules for spiking neural networks (SNNs) within a Bayesian continual learning framework. In it, each synaptic weight is represented by parameters that quantify the current epistemic uncertainty resulting from prior knowledge and observed data. The proposed online rules update the distribution parameters in a streaming fashion as data are observed. We instantiate the proposed approach for both real-valued and binary synaptic weights. Experimental results using Intel's Lava platform show the merits of Bayesian over frequentist learning in terms of capacity for adaptation and uncertainty quantification.

Original languageEnglish (US)
Article number1037976
JournalFrontiers in Computational Neuroscience
StatePublished - Nov 16 2022

All Science Journal Classification (ASJC) codes

  • Neuroscience (miscellaneous)
  • Cellular and Molecular Neuroscience


  • Bayesian learning
  • artificial intelligence
  • neuromorphic hardware
  • neuromorphic learning
  • spiking neural networks


Dive into the research topics of 'Bayesian continual learning via spiking neural networks'. Together they form a unique fingerprint.

Cite this