A Comprehensive Benchmark of Neural Networks for System Identification
A Comprehensive Benchmark of Neural Networks for System Identification
复制标题
用于系统识别的神经网络综合基准
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
M. Geist
中科院分区：
文献类型：
--
作者：
Antoine Richard;Antoine Mahé;Cédric Pradalier;O. Rozenstein;M. Geist
本文比较了机器人和控制黑盒建模背景下应用的各种神经网络架构。我们比较了六种不同的架构概念和四种激活函数以及三百多个不同的模型。这些模型应用于三个机器人数据集，以显示架构之间的性能差异及其局限性。
This paper compares a wide variety of neural network architectures applied in the context of black-box modeling for robotics and control. We compare six different architectural concepts and four activation functions, with over three hundred different models. Those models were applied to three robotics datasets to show the differences in performance between the architectures along with their limitations.