GAND-Nets: Training Deep Spiking Neural Networks with Ternary Weights
GAND-Nets: Training Deep Spiking Neural Networks with Ternary Weights
复制标题
DOI：
10.1109/socc56010.2022.9908132
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Man Wu;Yirong Kan;Renyuan Zhang;Y. Nakashima
中科院分区：
文献类型：
--
作者：
Man Wu;Yirong Kan;Renyuan Zhang;Y. Nakashima
尖峰神经网络（SNN）已成为ANN的承诺替代方案，以通过事件驱动的稀疏性在资源受限的设备上进行能源效率。分类应用程序，导致硬件实现的延迟和计算成本。三元重量范式结合了峰值输入的效率{0，1}和离散的三元重量{-1，0，1}。此外为了概念验证，我们对CIFAR-10，CIFAR-100和NMNIST数据集进行了使用，我们评估了拟议的Gand-nets，其随机率编码为87.42％，63.42％和98.43％更少的时间步骤，并提供1位二元二进制点产品加速度。
Spiking neural networks (SNNs) have emerged as a promising alternative to ANNs for their energy efficiency on resource-constrained devices via event-driven sparsity. However, the state-of-art SNNs utilize longer time steps and full precision weights to implement complex image classification applications, which leads to significant latency and computational cost for hardware implementation. To this end, this paper leverages the surrogate gradient-based SNN model and threshold-based ternary weight paradigm to combine the efficiency gains of spike input {0, 1} and discrete ternary weight {−1, 0, 1}. In this manner, the internal state of SNN can be accelerated by binary-ternary dot product to replace multiply and accumulation operations. Moreover, binary-ternary dot products can design as gated AND networks (GAND-Nets). Since only the event-driven non-zero activation enables the control gate to start the AND logic operations, which towards energy-efficient edge intelligence. For proof-of-concept, we evaluate the proposed GAND-Nets on CIFAR-10, CIFAR-100, and NMNIST datasets with stochastic rate encoding, which achieve 87.42%, 63.42% and 98.43% accuracy with fewer time step, and provide 1 bit-width binary-ternary dot product accelerations.