论文标题
高度稀疏的尖峰神经网络的两步尖峰编码方案和体系结构
Two-Step Spike Encoding Scheme and Architecture for Highly Sparse Spiking-Neural-Network
论文作者
论文摘要
本文提出了一个两步的尖峰编码方案，该方案由源编码和用于高能峰值峰值神经网络（SNN）加速的过程编码组成。特征训练及其叠加产生的尖峰火车，其尖峰比的精度很高。稀疏性提升（SB）和尖峰生成跳过（SG）减少了SNN的操作量。缩小多级编码（TS-MLE）的时间会压缩沿时间轴的火车中的尖峰数，而尖峰级的时钟跳过（SLC）会减少处理时间。在CIFAR-10分类的条件下，特征训练生成的精度达到90.3％的精度，相同的CNN准确性。 SB仅以0.1％的精度损失将尖峰比降低0.49倍，而SGS将尖峰比降低了20.9％，精度损失为0.5％。与以前的发电机相比，TS-MLE和SLC将SNN的吞吐量增加2.8倍，同时将Spike Generator的硬件资源降低75％。
This paper proposes a two-step spike encoding scheme, which consists of the source encoding and the process encoding for a high energy-efficient spiking-neural-network (SNN) acceleration. The eigen-train generation and its superposition generate spike trains which show high accuracy with low spike ratio. Sparsity boosting (SB) and spike generation skipping (SGS) reduce the amount of operations for SNN. Time shrinking multi-level encoding (TS-MLE) compresses the number of spikes in a train along time axis, and spike-level clock skipping (SLCS) decreases the processing time. Eigen-train generation achieves 90.3% accuracy, the same accuracy of CNN, under the condition of 4.18% spike ratio for CIFAR-10 classification. SB reduces spike ratio by 0.49x with only 0.1% accuracy loss, and the SGS reduces the spike ratio by 20.9% with 0.5% accuracy loss. TS-MLE and SLCS increases the throughput of SNN by 2.8x while decreasing the hardware resource for spike generator by 75% compared with previous generators.
