Alert button
Picture for David Bernal-Casas

David Bernal-Casas

Alert button

Deep Spiking Neural Networks with Resonate-and-Fire Neurons

Sep 16, 2021
Badr AlKhamissi, Muhammad ElNokrashy, David Bernal-Casas

Figure 1 for Deep Spiking Neural Networks with Resonate-and-Fire Neurons
Figure 2 for Deep Spiking Neural Networks with Resonate-and-Fire Neurons
Figure 3 for Deep Spiking Neural Networks with Resonate-and-Fire Neurons
Figure 4 for Deep Spiking Neural Networks with Resonate-and-Fire Neurons

In this work, we explore a new Spiking Neural Network (SNN) formulation with Resonate-and-Fire (RAF) neurons (Izhikevich, 2001) trained with gradient descent via back-propagation. The RAF-SNN, while more biologically plausible, achieves performance comparable to or higher than conventional models in the Machine Learning literature across different network configurations, using similar or fewer parameters. Strikingly, the RAF-SNN proves robust against noise induced at testing/training time, under both static and dynamic conditions. Against CNN on MNIST, we show 25% higher absolute accuracy with N(0, 0.2) induced noise at testing time. Against LSTM on N-MNIST, we show 70% higher absolute accuracy with 20% induced noise at training time.

* Preprint 
Viaarxiv icon