**Job Description**
This doctoral project aims to enhance the robustness of teacher learning within an event-based framework, particularly when both the teacher model and learning rules operate on events. By leveraging excitable teacher dynamics and synaptic learning rules, the project seeks to demonstrate that synchrony of events, rather than trajectories, can be made robust against mismatches between teacher and student models. Additionally, the research will explore how learning rules can be made local and pairwise, similar to Hebbian learning principles.
**Skills & Abilities**
• Strong coding skills for programming neural networks, machine learning, and machine learning software frameworks (e.g., PyTorch or Jax).
• Ability for creative and analytical thinking across discipline boundaries and abstraction levels.
• Experience with control theory and spiking neural networks (advantageous).
• Ability for collaborative work, interdisciplinary and cross-topical thinking.
• Very good communication skills in English, both spoken and written.
**Qualifications**
Required Degree(s) in:
• Physics
• Electrical/Electronic Engineering
• Computer Science
• Mathematics
• A related field
Degree Level: Master’s degree
**Experience**
Other:
• Experience with control theory and spiking neural networks (a plus)
Note: We’ve analyzed the actual job post using AI, for more details visit the original job post by clicking on “Apply Now”!
