Are you passionate about brain-inspired AI and sustainable tech? As a PhD Candidate, you will design real-time FPGA-based systems that mimic neural processes, enabling intelligent, on-chip learning for edge AI. Dive into cutting-edge research on spiking neural networks, event-based sensors, and asynchronous learning. Collaborate internationally, publish your work, and inspire future minds through teaching and supervision!
Neuromorphic computing offers a transformative path towards energy-efficient and brain-inspired artificial intelligence by mimicking the structure and functionality of biological neural systems. To harness its potential, this research emphasises the use of field-programmable gate arrays (FPGAs) as a core hardware platform – enabling real-time,
parallel, and low-latency processing. FPGAs are ideal for implementing spiking neural networks (SNNs), supporting on-chip learning and edge AI deployment. This project aims to develop a neuromorphic FPGA-based architecture integrating biologically plausible neuron and synapse models with innovative hardware-software co-design. You will lead the design of a scalable FPGA-based platform for neuromorphic inference and real-time learning.
You will further develop the framework to support multimodal data processing from event-based camera’s such as dynamic vision sensors (DVS). A key responsibility will be to explore and implement asynchronous learning algorithms, focusing on SNN few-shot, synergic (local-global) and asynchronous learning strategies suitable for real-time and embedded systems scenarios.
Finally, you will benchmark the developed system on real-world tasks such dynamic vision and speech recognition. You will be actively involved in teaching at the department, supervising BSc/MSc theses. In addition, you will write scientific articles and regularly participate in international conferences to present your research findings.
You’re invited to apply for a unique opportunity to work on the cutting edge of brain-inspired computation. You will develop fundamental insights and practical innovations in sustainable AI, focusing on real-time, low-power, on-chip and event-based learning systems implemented on reconfigurable neuromorphic platforms.
Would you like to learn more about what it’s like to pursue a PhD at Radboud University? Visit the page about working as a PhD candidate.