Deep Spiking Neural Networks with Resonate-and-Fire Neurons
This work addresses the need for more biologically plausible and robust neural networks in machine learning, though it appears incremental as it builds on existing neuron models and training methods.
The paper tackles the problem of improving spiking neural networks by introducing a new formulation with Resonate-and-Fire neurons, achieving performance comparable to or higher than conventional models with similar or fewer parameters and demonstrating robustness against noise, such as 25% higher accuracy on MNIST with noise.
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.