Eindhoven University of Technology, Departments of Mechanical Engineering and Electrical Engineering and Eindhoven Hendrik Casimir Institute, has a vacancy for aPostdoc 'Efficient learning in hardware for next-generation neuromorphic computing and smart sensors'
Neuromorphic computing could address the inherent limitations of conventional silicon technology in dedicated machine learning applications. Recent work on large crossbar-arrays of two-terminal memristive devices has led to the development of promising neuromorphic systems. However, delivering a parallel computation technology, capable of embedding artificial neural networks in hardware, remains a significant challenge. Organic electronic materials offer an attractive alternative and can provide neuromorphic devices with low-energy switching and excellent tunability. Here we propose a novel implementation of backpropagation in hardware enabling - for the first time - tuning of multilayer hardware neural network, an essential step for energy-efficient and edge computing systems such as smart sensors.Key objectives and scientific challenges
- Realisation of a neuromorphic array of optimised organic neuromorphic devices
- Demonstration of novel implementation of weight tuning in hardware
- Development of a modular neuromorphic chip with error backpropagation in hardware