论文《基于自旋电子学的脉冲神经网络的性能评估使用并行离散事件仿真》的可重复性报告

Reproducibility Report for the Paper "Performance Evaluation of Spintronic-Based Spiking Neural Networks Using Parallel Discrete-Event Simulation"

ACM Transactions on Modeling and Computer Simulation · 2024
被引 1
ABS 3

中文导读

该报告验证了Doryta模拟器(基于ROSS模型的脉冲神经网络仿真器)的可重复性,通过提供的脚本成功复现了论文中的所有主要结果,适合关注仿真可重复性的研究者参考。

Abstract

The examined paper introduces Doryta , a simulator for Spiking Neural Networks implemented as a ROSS model. The software artifact is available as part of the paper’s supplemental material and can be accessed via the journal’s website. It is well documented and enhances the overall quality of the paper by providing access to the source code of the Doryta simulator and necessary scripts to reproduce the results shown in the figure. Using the script, we reproduced all major results presented in the paper. Thus, the paper qualifies for the Artifact Available , the Artifact Evaluated–Reusable , and the Artifact Validated–Results Reproduced badges.

可重复性计算机科学脉冲神经网络离散事件仿真