Training multi-layer spiking neural networks using NormAD based spatio-temporal error backpropagation

Navin Anwani, Bipin Rajendran

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


Spiking neural networks (SNNs) have garnered a great amount of interest for supervised and unsupervised learning applications. This paper deals with the problem of training multi-layer feedforward SNNs. The non-linear integrate-and-fire dynamics employed by spiking neurons make it difficult to train SNNs to generate desired spike trains in response to a given input. To tackle this, first the problem of training a multi-layer SNN is formulated as an optimization problem such that its objective function is based on the deviation in membrane potential rather than the spike arrival instants. Then, an optimization method named Normalized Approximate Descent (NormAD), hand-crafted for such non-convex optimization problems, is employed to derive the iterative synaptic weight update rule. Next, it is reformulated to efficiently train multi-layer SNNs, and is shown to be effectively performing spatio-temporal error backpropagation. The learning rule is validated by training 2-layer SNNs to solve a spike based formulation of the XOR problem as well as training 3-layer SNNs for generic spike based training problems. Thus, the new algorithm is a key step towards building deep spiking neural networks capable of efficient event-triggered learning.

Original languageEnglish (US)
Pages (from-to)67-77
Number of pages11
StatePublished - Mar 7 2020

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence


  • Leaky integrate-and-fire
  • Multi-layer SNN
  • NormAD
  • Normalized approximate descent
  • Spatio-temporal error backpropagation
  • Spiking neuron
  • Supervised learning
  • XOR problem


Dive into the research topics of 'Training multi-layer spiking neural networks using NormAD based spatio-temporal error backpropagation'. Together they form a unique fingerprint.

Cite this