论文标题
p-关键：神经形态硬件的储层自动调节可塑性规则
P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware
论文作者
论文摘要
反复的人工神经网络上的反向传播算法需要随着时间的流逝而展开累积状态。必须将这些状态保存在不确定的时间段内，这是任务依赖的。本文使用储层计算范式，其中未经训练的复发性神经网络层用作学习时间和有限数据的预处理器阶段。这些所谓的水库需要无监督的学习规则进行广泛的微调或神经塑性。我们提出了一项新的本地可塑性规则，名为P-Critical旨在自动储层调整，它可以很好地转化为Intel的Loihi Research Chip，这是最近的神经形态处理器。我们在使用尖峰神经元体系结构时比较了机器学习社区的知名数据集的方法。我们观察到来自各种模式的任务的改进性能，而无需调整参数。这种算法可能是在边缘设备上基于端到端的基于神经形态的机器学习的关键。
Backpropagation algorithms on recurrent artificial neural networks require an unfolding of accumulated states over time. These states must be kept in memory for an undefined period of time which is task-dependent. This paper uses the reservoir computing paradigm where an untrained recurrent neural network layer is used as a preprocessor stage to learn temporal and limited data. These so-called reservoirs require either extensive fine-tuning or neuroplasticity with unsupervised learning rules. We propose a new local plasticity rule named P-CRITICAL designed for automatic reservoir tuning that translates well to Intel's Loihi research chip, a recent neuromorphic processor. We compare our approach on well-known datasets from the machine learning community while using a spiking neuronal architecture. We observe an improved performance on tasks coming from various modalities without the need to tune parameters. Such algorithms could be a key to end-to-end energy-efficient neuromorphic-based machine learning on edge devices.
