Parameter calibration with Consensus-based Optimization for interaction dynamics driven by neural networks
Optimization and Control
2021-09-13 v1
Abstract
We calibrate parameters of neural networks that model forces in interaction dynamics with the help of the Consensus-based global optimization method (CBO). We state the general framework of interaction particle systems driven by neural networks and test the proposed method with a real dataset from the ESIMAS traffic experiment. The resulting forces are compared to well-known physical interaction forces. Moreover, we compare the performance of the proposed calibration process to the one in [4] which uses a stochastic gradient descent algorithm.
Cite
@article{arxiv.2109.04690,
title = {Parameter calibration with Consensus-based Optimization for interaction dynamics driven by neural networks},
author = {Simone Göttlich and Claudia Totzeck},
journal= {arXiv preprint arXiv:2109.04690},
year = {2021}
}