Easy and efficient spike-based Machine Learning with mlGeNN
Easy and efficient spike-based Machine Learning with mlGeNN
复制标题
DOI：
10.1145/3584954.3585001
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
James C. Knight;Thomas Nowotny
中科院分区：
文献类型：
--
作者：
James C. Knight;Thomas Nowotny
直观和易于使用的应用程序编程接口，如Kera，在使用人工神经网络快速加速机器学习方面发挥了很大作用。在我们最近将ANN转换为SNN并使用e-prop直接训练分类器的基础上，我们在这里提出了mlGeNN接口，作为在我们基于高效的GPU的Genn框架上定义、训练和测试尖峰神经网络的一种简单方法。我们通过研究一些一层和两层递归尖峰神经网络的性能来说明mlGeNN的使用，这些神经网络被训练成使用e-prop学习规则从DVS手势数据集中识别手势。我们发现，mlGeNN不仅比较低级别的PyGeNN接口使用方便得多，而且新的、毫不费力地快速构建不同网络架构原型的自由也让我们对e-Prop在架构细节上与其他最近发布的DVS手势数据集的结果进行了前所未有的概述。
Intuitive and easy to use application programming interfaces such as Keras have played a large part in the rapid acceleration of machine learning with artificial neural networks. Building on our recent works translating ANNs to SNNs and directly training classifiers with e-prop, we here present the mlGeNN interface as an easy way to define, train and test spiking neural networks on our efficient GPU based GeNN framework. We illustrate the use of mlGeNN by investigating the performance of a number of one and two layer recurrent spiking neural networks trained to recognise hand gestures from the DVS gesture dataset with the e-prop learning rule. We find that not only is mlGeNN vastly more convenient to use than the lower level PyGeNN interface, the new freedom to effortlessly and rapidly prototype different network architectures also gave us an unprecedented overview over how e-prop compares to other recently published results on the DVS gesture dataset across architectural details.