Robustly and Optimally Controlled Training Of neural Networks I (OCTON I)
Forskningsprojekt, 2019 – 2023

This project aims at developing novel data training methods for network of function approximators (such as neural networks) based on robust and optimal control theory. The main idea is to utilize approximate neural tangent kernel parametrization in order to dynamically constrain training objectives. In this project we will develop novel methods that accounts for non-traditional training objectives (other than mean square prediction error) and corrupted data sequence. The latter claims for robustification. Conservativeness, stability of training, guaranteed rate of convergence, scalable numerical optimization routines will be developed.

Deltagare

Viktor Andersson (kontakt)

Chalmers, Elektroteknik, System- och reglerteknik

Rebecka Jörnsten

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Balázs Adam Kulcsár

Chalmers, Elektroteknik, System- och reglerteknik

Finansiering

Centiro

Finansierar Chalmers deltagande under 2019–2023

Relaterade styrkeområden och infrastruktur

Transport

Styrkeområden

Publikationer

2024

Controlled Descent Training

Artikel i vetenskaplig tidskrift
2023

Deep Q-learning: a robust control approach

Artikel i vetenskaplig tidskrift

Mer information

Senast uppdaterat

2022-05-03