Stochastic hardware implementation of Liquid State Machines
Stochastic hardware implementation of Liquid State Machines
复制标题
液态状态机的随机硬件实现
DOI：
10.1109/ijcnn.2016.7727324
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
J. Rosselló
中科院分区：
文献类型：
--
作者：
M. Alomar;V. Canals;A. Morro;A. Oliver;J. Rosselló
神经网络模型的硬件实现可以有效地利用其固有的并行性。在这里，我们重点关注液体状态机 (LSM) 方法来构建循环尖峰神经网络 (SNN)，特别适合处理时间相关信号。我们提出了一种基于随机计算（SC）概念的 LSM 网络的低成本硬件实现。本方法的功能针对时间序列预测任务进行了演示。
The hardware implementation of neural network models allows to efficiently exploit their inherent parallelism. Here, we focus on the Liquid State Machine (LSM) methodology to build recurrent Spiking Neural Networks (SNN), particularly suited to process time-dependent signals. We propose a low cost hardware implementation of LSM networks based on the use of stochastic computing (SC) concepts. The functionality of the present approach is demonstrated for a time-series prediction task.