T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding

by   Seongsik Park, et al.

Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems. The deep neural network-to-SNN conversion approach has been widely studied to broaden the applicability of SNNs. Most previous studies, however, have not fully utilized spatio-temporal aspects of SNNs, which has led to inefficiency in terms of number of spikes and inference latency. In this paper, we present T2FSNN, which introduces the concept of time-to-first-spike coding into deep SNNs using the kernel-based dynamic threshold and dendrite to overcome the aforementioned drawback. In addition, we propose gradient-based optimization and early firing methods to further increase the efficiency of the T2FSNN. According to our results, the proposed methods can reduce inference latency and number of spikes to 22 which is the state-of-the-art result on the CIFAR-100.


Training Energy-Efficient Deep Spiking Neural Networks with Time-to-First-Spike Coding

The tremendous energy consumption of deep neural networks (DNNs) has bec...

Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks

The spiking neural networks (SNNs), the 3rd generation of neural network...

Noise-Robust Deep Spiking Neural Networks with Temporal Information

Spiking neural networks (SNNs) have emerged as energy-efficient neural n...

Predictive Coding as Stimulus Avoidance in Spiking Neural Networks

Predictive coding can be regarded as a function which reduces the error ...

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...

AutoSNN: Towards Energy-Efficient Spiking Neural Networks

Spiking neural networks (SNNs) that mimic information transmission in th...

Advancing Residual Learning towards Powerful Deep Spiking Neural Networks

Despite the rapid progress of neuromorphic computing, inadequate capacit...