arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.06135cs.NEcs.LGcs.PF
收藏

基于性能驱动BP和变体PSO的边缘决策浅层神经网络的可学习性和鲁棒性

Learnability and Robustness of Shallow Neural Networks Learned With a Performance-Driven BP and a Variant PSO For Edge Decision-Making

Cranfield University(克兰菲尔德大学);Anhui Polytechnic University(安徽工程大学);Smart Perception Ltd(Smart Perception有限公司)

Hongmei He, Mengyuan Chen, Gang Xu, Zhilong Zhu, Zhenhuan Zhu

摘要:

在许多情况下,如果没有GPU的好处,计算资源是有限的,特别是在支持物联网的系统的边缘设备中。在边缘设备中实现复杂的AI模型可能并不容易。通用逼近定理指出,浅神经网络(SNN)可以表示任何非线性函数。然而,SNN有多胖才足以解决边缘设备中的非线性决策问题?在本文中,我们专注于学习和鲁棒性的SNNs,获得了贪婪紧力启发式算法(性能驱动BP)和松散的力元启发式算法(PSO的变体)。进行两组实验以检查具有Sigmoid激活的SNN的可学习性和鲁棒性,通过KPI-PDBP和KPI-VPSO学习/优化,其中KPI(关键性能指标:错误(ERR),准确性(ACC)和$F_1$得分)是目标,驱动搜索过程。一个增量的方法被应用于检查隐藏的神经元数量对SNN的性能的影响,学习/优化的KPI-PDBP和KPI-VPSO。从工程角度来看,所有传感器都适合特定任务。因此,所有传感器读数都应与目标高度相关。因此,SNN的结构应该取决于问题空间的维度。实验结果表明,KPI-PDBP算法的隐层神经元数目可以达到问题空间的维数;在训练数据集上,KPI-PDBP算法产生的神经网络的学习性能和学习时间优于KPI-VPSO算法优化的神经网络;与其他经典的机器学习模型相比,ACC-PDBPs在几乎所有的测试数据集上都取得了较好的效果。

英文摘要:

In many cases, the computing resources are limited without the benefit from GPU, especially in the edge devices of IoT enabled systems. It may not be easy to implement complex AI models in edge devices. The Universal Approximation Theorem states that a shallow neural network (SNN) can represent any nonlinear function. However, how fat is an SNN enough to solve a nonlinear decision-making problem in edge devices? In this paper, we focus on the learnability and robustness of SNNs, obtained by a greedy tight force heuristic algorithm (performance driven BP) and a loose force meta-heuristic algorithm (a variant of PSO). Two groups of experiments are conducted to examine the learnability and the robustness of SNNs with Sigmoid activation, learned/optimised by KPI-PDBPs and KPI-VPSOs, where, KPIs (key performance indicators: error (ERR), accuracy (ACC) and $F_1$ score) are the objectives, driving the searching process. An incremental approach is applied to examine the impact of hidden neuron numbers on the performance of SNNs, learned/optimised by KPI-PDBPs and KPI-VPSOs. From the engineering prospective, all sensors are well justified for a specific task. Hence, all sensor readings should be strongly correlated to the target. Therefore, the structure of an SNN should depend on the dimensions of a problem space. The experimental results show that the number of hidden neurons up to the dimension number of a problem space is enough; the learnability of SNNs, produced by KPI-PDBP, is better than that of SNNs, optimized by KPI-VPSO, regarding the performance and learning time on the training data sets; the robustness of SNNs learned by KPI-PDBPs and KPI-VPSOs depends on the data sets; and comparing with other classic machine learning models, ACC-PDBPs win for almost all tested data sets.

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。

↑