神经形态架构作为计算神经科学的数值求解器
Neuromorphic architectures as numerical solvers for computational neuroscience
浏览论文内容
中文总结 AI 辅助
本文将计算神经科学的连续耦合神经元模型的分布式模拟视为并行硬件的消息传递算法，提出基于多比特数据包通信、高阶微分方程求解的无脉冲神经形态系统设计，实现了能耗与延迟的降低。
中文摘要 AI 辅助
神经形态计算与脉冲神经元网络密切相关，但计算神经科学和机器学习领域产生的另一类所谓“基于放电率”的模型摒弃了脉冲交互，转而依赖神经元间的连续耦合。现有围绕脉冲交互设计的神经形态实现并不适合模拟这类模型。本文将这些模型的分布式模拟视为并行硬件上的消息传递算法，利用数值算法和分布式模拟的现有技术，概述了为非脉冲神经元模型设计高效数字神经形态加速器的步骤。特别地，本文表明，在分组交换网络中，多比特数据包而非脉冲是最高效的通信策略；与基础数值积分方法相比，高阶微分方程求解器可降低计算与通信成本，同时实现更低的数值误差，但这些优势最终受限于算术精度。基于所提出的设计原则，本文将现有神经形态架构转换为分布式数值求解器——一种无脉冲神经形态系统，用于连续耦合神经元模型，从而证明理论考量确实能转化为实际优势，即降低能耗与延迟。
英文摘要
Neuromorphic computing is closely associated with spiking neuronal networks. However, an alternative class of so-called "rate-based" models arising from computational neuroscience and machine learning forgoes spiking interactions and instead relies on continuous coupling between neurons. Existing neuromorphic implementations designed around spike-based interactions are not well-suited for emulating such models. Here view the distributed simulation of these models as message-passing algorithms on parallel hardware. Leveraging prior art in numerical algorithms and distributed simulation, we outline steps that enable the design of efficient digital neuromorphic accelerators for non-spiking neuronal models. In particular, we show that multi-bit packets, rather than spikes, are the most efficient communication strategy in packet-switched networks and that compared to basic numerical integration methods, higher-order differential equation solvers decrease both computation and communication costs while achieving lower numerical error, but that these benefits are ultimately limited by arithmetic precision. Using our proposed design principles, we convert an existing neuromorphic architecture into a distributed numerical solver - a spikeless neuromorphic system - for continuously-coupled neuronal models. We thereby demonstrate that our theoretical considerations indeed translate into practical advantages, namely reduced energy consumption and delay.
