AI/ML Research Intern at BMW on Neuromorphic Computing

This research is conducted as part of the EU research project Phastrac. The goal of Phastrac is to develop the next-generation computing architecture for AI applications with neuromorphic chips based on Oscillatory Neural Networks (ONNs). In total, the project has four partners: IBM, BMW, TUe, and PPKE. Phastrac is divided into four work packages and addresses the entire pipeline of the computing architecture development. For example, IBM leads research on low-level chip design, including the materials and fabrication processes of an ONN-based chip, within Work Package 1. BMW leads Work Package 4 and focuses on showcasing AI application demonstrators using ONNs for sensory signal processing.

As part of my internship, I co-developed an ONN simulator using Neural ODEs. I led a user study with BMW participants to collect a dataset with a tactile hardware prototype for human-vehicle interaction, and trained the ONNs on the tactile dataset.

You can see one sample demonstrator project of TUe with ONN-based control below: