MENU

Muhammad Zakwan

Muhammad Zakwan
Muhammad Zakwan
PhD Student
EPF Lausanne
muhammad.zakwan@epfl.ch
Curriculum Vitae
Realizing mathematical constructions to tangible real-world applications for a better future.

Muhammad Zakwan is a doctoral assistant in the Dependable Control and Decision group (DECODE) at École Polytechnique Fédérale de Lausanne (EPFL). He is also a member of the National Centre of Competence in Research (NCCR) Automation. Zakwan holds an Electrical and Electronics  Engineering degree from Bilkent University (Turkey) and a Bachelor of Science in Electrical Engineering from the Pakistan Institute of Engineering and Applied Sciences (Pakistan). His research interests include LPV systems, hybrid dynamical systems, time-delay systems, distributed systems, and machine learning.

Scientific Publications

Published
Stable Linear Subspace Identification: A Machine Learning Approach
ArXiv
Loris Di Natale, Muhammad Zakwan, Bratislav Svetozarevic, Philipp Heer, Giancarlo Ferrari-Trecate, Colin Jones
Doi.org Collection
Published
Universal Approximation Property of Hamiltonian Deep Neural Networks
IEEE Control System Letters
Vol 7 Pages 2689-2694
Muhammad Zakwan, Massimiliano d'Angelo, Giancarlo Ferrari-Trecate
Collection
Published
Physically Consistent Neural ODEs for Learning Multi-Physics Systems
Proceedings of IFAC World congress 2023
Muhammad Zakwan, Loris Di Natale, Bratislav Svetozarevic, Philipp Heer, Colin Jones, Giancarlo Ferrari-Trecate
Doi.org Arxiv.org
Published
Robust Classification Using Contractive Hamiltonian Neural ODEs
IEEE Control Systems Letters
Vol 7 Pages 145-150
Muhammad Zakwan, Liang Xu, Giancarlo Ferrari-Trecate
Doi.org Collection
Published
Distributed Neural Network Control with Dependability Guarantees: a Compositional Port-Hamiltonian Approach
Proceedings of The 4th Annual Learning for Dynamics and Control Conference
Vol 168 Pages 571-583
Luca Furieri, Clara Lucía Galimberti, Muhammad Zakwan, Giancarlo Ferrari-Trecate
Doi.org Collection
Published
Neural Energy Casimir Control for Port-Hamiltonian Systems
arXiv
Liang Xu, Muhammad Zakwan, Giancarlo Ferrari-Trecate
Doi.org Collection

Research projects as Researcher

Title
Principal Investigators

ODE networks for data-based control

Giancarlo Ferrari-Trecate

Summary

In spite of several success stories, standard deep networks  can lead to unstable forward propagation or suffer from an ill-posed learning process, which might result in vulnerability to adversarial attacks. In this project we will study deep network architectures based on ODEs for mitigating these problems. Furthermore, we will investigate the use of these networks for parametrizing regulators that can be tuned from available data. The new methods will be tested for the control of inverters, smart loads and microgrid clusters, which are relevant for the energy systems considered in the NCCR.

People involved

Muhammad Zakwan
Giancarlo Ferrari-Trecate, Muhammad Zakwan
ODE networks for data-based control
Giancarlo Ferrari-Trecate

In spite of several success stories, standard deep networks  can lead to unstable forward propagation or suffer from an ill-posed learning process, which might result in vulnerability to adversarial attacks. In this project we will study deep network architectures based on ODEs for mitigating these problems. Furthermore, we will investigate the use of these networks for parametrizing regulators that can be tuned from available data. The new methods will be tested for the control of inverters, smart loads and microgrid clusters, which are relevant for the energy systems considered in the NCCR.

Muhammad Zakwan
Giancarlo Ferrari-Trecate, Muhammad Zakwan
120
bba0c33c-021f-4dbb-848c-3b2f57e14a0b