positions

Task: Adaptive sensor- and context-aware learning (WP1)

Host institution: CSEM

Country: Switzerland

Supervisor: Dr. J. Beysens [CSEM]

Co-supervisors: Prof. P. Casari [UNITN]; Dr. D. Pau [ST]

Objectives: 1) To propose continual on-device learning algorithms that are able to detect distribution shifts; 2) To enable on-device continual learning with regular and forward computing with a mix of innovation on self-organised neural network topologies; 3) To jointly optimise
embedded on-device continual learning and network topologies in evolving environments.

Expected Results: 1) New on-tiny-device continual learning algorithms; 2) Self-organising neural topologies; 3) Deployability studies for resource restricted devices.

PhD enrolment: Doctoral School of UNITN

Planned secondments: 

• ST (4 months, M16-M19): Context-aware embedded AI boards for zero-power embedded devices, with Prof. P. Casari (KPI: joint paper)

• TU Delft (4 months, M28-M31): On-device continual learning & topology optimisation for autonomous robotics, with Dr. D. Pau (KPI: joint paper)

Candidate profile: computer science, electrical engineering, applied mathematics, or equivalent (in order of preference)

Desirable skills/interests: signal processing, embedded systems, machine learning, resource-constrained optimization, tinyML (the applicant should be proficient in at least one or two of the skills)

Application Deadline: February 14, 2025, AoE

Descriptions of all the 18 DC Positions

Submit Your Application HERE