Two PhD student positions in Hardware for Machine learning within WASP, formally based at the Division for Computer Engineering, the Department of Electrical Engineering, Linköping University.
As PhD student will carry out research directed by Prof Jose Nunez-Yanez, who is a Royal Society industrial fellow in Machine intelligence at the network Edge and has been appointed as Professor in Computing Architectures for Machine Learning at the Department of Electrical Engineering (ISY), Linköping University.
The research focus for the advertised positions is directed towards hardware design and algorithms for deploying and training complex neural network models at the edge. We aim at creating energy proportional hardware that adapts the computation to the complexity of the data and that is capable of tracking changes in the data properties and tune the model parameter to these changes. One PhD position focuses on heavily quantized neural networks combined with early-exit strategies and a second position on embedded training with multiple precision hardware extended via dynamic function exchange. Application areas include object detection and classification, natural language processing and fault diagnosis.