On Model-guided Neural Networks for System Identification
L Lu, Y Tan, D Oetomo, I Mareels, E Zhao, S An
2019 IEEE Symposium Series on Computational Intelligence (SSCI) | IEEE | Published : 2020
Many techniques exist to train neural networks to approximate a complex systems, such as deep learning methods. It is well known that despite their robustness with respect to over-fitting, such trained models may be brittle as some fundamental principles of the systems are missing. For many engineering applications, the model class may be derived from first principles (or fundamental principles). In this paper, ideas from both methodologies are combined to arrive at a robust model that is interpretable from first principles, but goes beyond this by capturing structure from the available data. The paper presents two examples to illustrate the ideas. First a synthetic data set based on simulat..View full abstract
Awarded by National Natural Science Foundation of China
Awarded by International Postdoctoral Exchange Fellowship Program
Awarded by Hielongjiang Province Science Foundation for Youths
This research was funded by the National Natural Science Foundation of China (#51705106), the International Postdoctoral Exchange Fellowship Program (#20170042), Hielongjiang Province Science Foundation for Youths (#QC2017019). Corresponding author, Lei Lu, email: email@example.com.