Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks
This work addresses energy-efficient computing for AI applications, but it appears incremental as it builds on existing conversion methods for SNNs.
The paper tackled the problem of slow inference speed and low energy efficiency in deep spiking neural networks (SNNs) by proposing a method using burst spikes and a hybrid neural coding scheme, resulting in improved energy efficiency and reduced latency.
The spiking neural networks (SNNs) are considered as one of the most promising artificial neural networks due to their energy efficient computing capability. Recently, conversion of a trained deep neural network to an SNN has improved the accuracy of deep SNNs. However, most of the previous studies have not achieved satisfactory results in terms of inference speed and energy efficiency. In this paper, we propose a fast and energy-efficient information transmission method with burst spikes and hybrid neural coding scheme in deep SNNs. Our experimental results showed the proposed methods can improve inference energy efficiency and shorten the latency.