PhD Analog/Mixed-signal Design for Oscillatory Neural Networks [closed]

We are seeking highly motivated and talented PhD candidates withing the framework of the PHASTRAC project to join our research team in the exciting field of analog/mixed-signal circuit design for neuromorphic computing based on oscillatory neural networks, enabling energy efficient edge computing. This position offers an exceptional opportunity to contribute to cutting-edge research in the development of novel brain-inspired computing architectures for advanced machine learning and artificial intelligence applications. Join the dynamic and vibrant environment at Eindhoven University of Technology (TU/e) and become a vital part of shaping the future hardware for AI.


Postdoc Atomistic and Device Simulation


 We are seeking a highly skilled and motivated Post-Doc candidate with expertise in atomistic simulation and TCAD device simulation to join our dynamic NanoComputing research team within the Department of Electical Engineering of the Eindhoven University of Techonology (TU/e). This position offers an exciting opportunity to contribute to cutting-edge research in the field of phase change material (PCM) devices and metal oxide-hafnium dioxide (HfO2) memristor devices. The successful candidate will play a key role in advancing our understanding of these novel technologies through atomistic modeling and device simulation techniques. Do you recognize yourself in this profile and would you like to know more? Visit the TU/e website or contact Prof. Aida Todri-Sanial.

Postdoc Neuromorphic Computing with Oscillatory Neural Networks [closed]

We are seeking highly skilled and motivated candidates to work on Neuromorphic ONN Computing and Multi-modal ONN learning. The Postdoc will explore analog ONN neuromorphic computing paradigm with novel devices based on VO2 (oscillators) and MO/HfO2 (synaptic interconnections) materials. The focus is to develop circuit to architecture-level modules to design the mechanism for updating the non-volatile interconnection network depending on the transient state of the network. The overall objective is to implement learning functions in analog weights and realizable by MO/HfO2 devices. Various coupling schemes will be implemented and investigated with respect to the various learning rules and problems to be solved. Different problems will require different coupling schemes and learning rules; thus, the goal is to thoroughly assess the analog ONN requirements, learning mechanisms and its design implementation. We will also investigate the interface with sensor data to investigate reliability, performance, and noise sensitivity. Join the PHASTRAC project in the Electronic Systems (ES) group within the TU/e. Please visit the TU/e website for more information.