PhD Position in Systems and Control Theory for Energy-based Learning – University of Groningen, Netherlands

Summary

The University of Groningen is offering a PhD position focused on developing new mathematical foundations for energy-efficient computing, specifically at the intersection of systems and control theory, optimization, circuit theory, and neuromorphic computing. This project aims to create a novel system-theoretic framework for learning in analog circuits and dissipative networks, viewing learning as a feedback interconnection of continuous-time dynamics and an optimization algorithm. The ultimate goal is to advance the mathematical foundations of physics-based learning and contribute to energy-efficient neuromorphic computing.

PhD Position in Systems and Control Theory for Energy-based Learning – University of Groningen

Designation

PhD Candidate

Research Area

• Systems and Control Theory
• Optimization
• Circuit Theory
• Neuromorphic Computing
• Machine Learning

Location

Groningen, The Netherlands

The successful candidate will join the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence within the Faculty of Science and Engineering at the University of Groningen. The research will be carried out in the Systems, Control and Optimization Group.

Eligibility/Qualification

We are looking for an enthusiastic researcher who enjoys solving challenging problems and working in an international research environment. Candidates should possess:

• A Master’s degree in Systems and Control, (Applied) Mathematics, Electrical Engineering, or a closely related field.
• A strong mathematical background and an interest in conducting theoretical research.
• Excellent English communication skills, both written and spoken.
• Strong analytical abilities, creativity, persistence, and the ability to collaborate effectively.
• Familiarity with circuit theory, networked systems, machine learning, or neuromorphic computing is considered an advantage, but is not required.

Scholarship Description

What you will do:

As a PhD candidate, you will develop mathematical theory for learning in nonlinear and dynamic circuits. Your responsibilities include:

• Developing a system-theoretic framework that models learning as the feedback interconnection between continuous-time circuit dynamics and optimization algorithms.
• Designing novel energy-based learning algorithms for training analog circuits directly from input-output data.
• Developing fully decentralised learning rules that rely on local circuit information and are suitable for large-scale systems.
• Establishing rigorous theoretical guarantees for convergence and scalability of the proposed learning algorithms.
• Extending the theory from analog circuits to more general dissipative networks.
• Testing and validating the developed methods.
• Publishing research findings in leading international journals and conferences and presenting your work at scientific meetings.
• Contributing to teaching activities and supervising Bachelor’s and Master’s students where appropriate.

What we offer:

In accordance with the collective labor agreement for Dutch universities:

How to Apply

Interested candidates should apply by clicking the ‘Apply now’ link. Please include the following documents with your application:

1. Motivation letter (1-2 pages)
2. Curriculum Vitae
3. Academic transcripts (BSc and MSc)
4. Contact details of two academic references
5. Copy of MSc thesis (or a representative publication, if available)

Application Procedure:

1. Step 1: Your application – Submit your application online.
2. Step 2: Selection – The selection committee assesses your application.
3. Step 3: First interview – An interview (online or on location).
4. Step 4: Second interview and possible assessment or guest lecture – A potential second interview, possibly with an assessment or guest lecture.
5. Step 5: Terms of employment meeting – Discussion of employment terms.

Last Date for Apply

Until position filled

Apply Link

Apply Now