PhD in Energy-Based Learning for Neuromorphic Circuits

University of Groningen via AcademicTransfer; Netherlands; On-site; EUR 35,000 - 52,000; Full time

Benefits offered by this job

End-of-year bonus 8.3%

Holiday allowance 8%

Professional development opportunities

Job summary

University of Groningen invites applications for a PhD candidate position in Engineering, focusing on learning in neuromorphic circuits. The project combines systems and control theory, circuit theory, optimization, and machine learning to advance mathematical foundations of physics-based learning.

You will develop theory for nonlinear dynamic circuits, study memristive and capacitive elements, and work toward energy-efficient computing with robust convergence guarantees.

Qualifications

• Master's degree in Systems and Control, (Applied) Mathematics, Electrical Engineering, or a closely related field.
• Excellent English communication skills, both written and spoken.
• Strong analytical abilities, creativity, persistence, and collaboration.

Responsibilities

• Develop a system-theoretic framework that models learning as the feedback interconnection between continuous-time circuit dynamics and optimization algorithms.
• Design energy-based learning algorithms for training analog circuits from input-output data.
• Develop fully decentralised learning rules based on local circuit information for large-scale systems.
• Establish rigorous theoretical guarantees for convergence and scalability of the proposed learning algorithms.
• Extend theory from analog circuits to more general dissipative networks.
• Test and validate the developed methods.
• Publish research findings in leading journals and conferences; present at scientific meetings.
• Contribute to teaching activities and supervise Bachelor's and Master's students as appropriate.

Skills

Analytical abilities

Creativity

Persistence

Collaboration

Education

Master's in Systems and Control (Applied) Math or Electrical Engineering

Job description

University of Groningen invites applications for a PhD candidate position in Engineering, focusing on learning in neuromorphic circuits. The project combines systems and control theory, circuit theory, optimization, and machine learning to advance mathematical foundations of physics-based learning.

You will develop theory for nonlinear dynamic circuits, study memristive and capacitive elements, and work toward energy-efficient computing with robust convergence guarantees.