Ma Gehua, Yan Rui, Tang Huajin
College of Computer Science and Technology, Zhejiang University, Hangzhou, PRC.
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, PRC.
Patterns (N Y). 2023 Sep 4;4(10):100831. doi: 10.1016/j.patter.2023.100831. eCollection 2023 Oct 13.
Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy SNN (NSNN) and the noise-driven learning (NDL) rule by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. The NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation and learning. We demonstrate that this framework leads to spiking neural models with competitive performance, improved robustness against challenging perturbations compared with deterministic SNNs, and better reproducing probabilistic computation in neural coding. Generally, this study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers.
脉冲神经元网络支撑着大脑非凡的信息处理能力，并已成为神经形态人工智能的支柱模型。尽管对脉冲神经网络（SNN）进行了广泛研究，但大多数研究都是基于确定性模型建立的，忽略了神经计算固有的非确定性、噪声本质。本研究通过纳入噪声神经元动力学引入了噪声脉冲神经网络（NSNN）和噪声驱动学习（NDL）规则，以利用噪声神经处理的计算优势。NSNN提供了一个理论框架，可实现可扩展、灵活且可靠的计算与学习。我们证明，该框架能产生具有竞争力性能的脉冲神经模型，与确定性SNN相比，对具有挑战性的扰动具有更强的鲁棒性，并且能更好地再现神经编码中的概率计算。总体而言，本研究为机器学习、神经形态智能从业者和计算神经科学研究人员提供了一个强大且易于使用的工具。
