arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1907.07853cs.NEcs.CV
收藏

基于事件的自适应选择阈值特征提取

Event-based Feature Extraction Using Adaptive Selection Thresholds

MARCS Institute(MARCS研究所);Western Sydney University(西悉尼大学)

Saeed Afshar, Ying Xu, Jonathan Tapson, André van Schaik, Gregory Cohen

摘要:

无监督特征提取算法是机器学习系统中最重要的组成部分之一。这些算法通常适用于基于事件的领域,以在神经形态硬件中执行在线学习。然而,并非为此目的而设计,此类算法通常需要在实现期间进行显著简化以满足硬件约束,从而产生与性能的权衡。此外,传统的特征提取算法没有被设计成生成仅在神经形态硬件限制的上下文中有价值的有用的中间信号。在这项工作中,一种新的基于事件的特征提取方法,提出了这些问题的重点。该算法通过简单的自适应选择阈值,允许一个更简单的实现网络稳态比以前的作品,通过权衡少量的信息丢失的形式错过的事件,落在选择阈值之外。选择阈值的行为和作为一个整体的网络的输出被示出为提供唯一有用的信号,指示网络权重收敛,而不需要访问网络权重。提出了一种新的网络规模选择的探试法,它利用噪声事件及其特征表示。使用选择阈值产生网络激活模式,预测分类精度,允许快速评估和优化系统参数,而不需要运行后端分类。特征提取方法在N-MNIST基准数据集和通过视场的飞机数据集上进行了测试。多个配置与不同的分类器进行了测试,结果量化在每个处理阶段的性能增益。

英文摘要:

Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain to perform online learning in neuromorphic hardware. However, not designed for the purpose, such algorithms typically require significant simplification during implementation to meet hardware constraints, creating trade offs with performance. Furthermore, conventional feature extraction algorithms are not designed to generate useful intermediary signals which are valuable only in the context of neuromorphic hardware limitations. In this work a novel event-based feature extraction method is proposed that focuses on these issues. The algorithm operates via simple adaptive selection thresholds which allow a simpler implementation of network homeostasis than previous works by trading off a small amount of information loss in the form of missed events that fall outside the selection thresholds. The behavior of the selection thresholds and the output of the network as a whole are shown to provide uniquely useful signals indicating network weight convergence without the need to access network weights. A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations. The use of selection thresholds is shown to produce network activation patterns that predict classification accuracy allowing rapid evaluation and optimization of system parameters without the need to run back-end classifiers. The feature extraction method is tested on both the N-MNIST benchmarking dataset and a dataset of airplanes passing through the field of view. Multiple configurations with different classifiers are tested with the results quantifying the resultant performance gains at each processing stage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑