TCL: an ANN-to-SNN Conversion with Trainable Clipping Layers
arXiv:2008.04509 · doi:10.1109/DAC18074.2021.9586266
Abstract
Spiking-neural-networks (SNNs) are promising at edge devices since the event-driven operations of SNNs provides significantly lower power compared to analog-neural-networks (ANNs). Although it is difficult to efficiently train SNNs, many techniques to convert trained ANNs to SNNs have been developed. However, after the conversion, a trade-off relation between accuracy and latency exists in SNNs, causing considerable latency in large size datasets such as ImageNet. We present a technique, named as TCL, to alleviate the trade-off problem, enabling the accuracy of 73.87% (VGG-16) and 70.37% (ResNet-34) for ImageNet with the moderate latency of 250 cycles in SNNs.
arXiv commentTo appear in the 58th Design Automation Conference (DAC 2021)
References in corpus (6)
- Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
- Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
- Surrogate Gradient Learning in Spiking Neural Networks
- Exploring the Connection Between Binary and Spiking Neural Networks
- DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks
- Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation