Hoyer regularizer is all you need for ultra low-latency spiking neural networks

by   Gourav datta, et al.

Spiking Neural networks (SNN) have emerged as an attractive spatio-temporal computing paradigm for a wide range of low-power vision tasks. However, state-of-the-art (SOTA) SNN models either incur multiple time steps which hinder their deployment in real-time use cases or increase the training complexity significantly. To mitigate this concern, we present a training framework (from scratch) for one-time-step SNNs that uses a novel variant of the recently proposed Hoyer regularizer. We estimate the threshold of each SNN layer as the Hoyer extremum of a clipped version of its activation map, where the clipping threshold is trained using gradient descent with our Hoyer regularizer. This approach not only downscales the value of the trainable threshold, thereby emitting a large number of spikes for weight update with a limited number of iterations (due to only one time step) but also shifts the membrane potential values away from the threshold, thereby mitigating the effect of noise that can degrade the SNN accuracy. Our approach outperforms existing spiking, binary, and adder neural networks in terms of the accuracy-FLOPs trade-off for complex image recognition tasks. Downstream experiments on object detection also demonstrate the efficacy of our approach.


page 1

page 2

page 3

page 4


Can Deep Neural Networks be Converted to Ultra Low-Latency Spiking Neural Networks?

Spiking neural networks (SNNs), that operate via binary spikes distribut...

Towards Energy-Efficient, Low-Latency and Accurate Spiking LSTMs

Spiking Neural Networks (SNNs) have emerged as an attractive spatio-temp...

DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks

Spiking Neural Networks (SNNs) offer a promising alternative to traditio...

EEGSN: Towards Efficient Low-latency Decoding of EEG with Graph Spiking Neural Networks

A vast majority of spiking neural networks (SNNs) are trained based on i...

Ultra-low Latency Adaptive Local Binary Spiking Neural Network with Accuracy Loss Estimator

Spiking neural network (SNN) is a brain-inspired model which has more sp...

Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks

Spiking Neural Networks (SNNs) are a promising alternative to traditiona...

Unleashing the Potential of Spiking Neural Networks by Dynamic Confidence

This paper presents a new methodology to alleviate the fundamental trade...

Please sign up or login with your details

Forgot password? Click here to reset