• 4 September 2019
    • preprint
    • Published by HAL in HAL
Abstract
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.
All Related Versions