Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures

Understand

Spiking Neural Networks (SNNs) have recently emerged as a prominent neural computing paradigm.

• However, the typical shallow SNN architectures have limited capacity for expressing complex representations while training deep SNNs using input spikes has not been successful so far.
• Diverse methods have been proposed to get around this issue such as converting off-the-shelf trained deep Artificial Neural Networks (ANNs) to SNNs.
• However, the ANN-SNN conversion scheme fails to capture the temporal dynamics of a spiking system.