Smart Edge Lab for Healthcare

AI acts as a driving force for economic and social development. It sits at the forefront of the technological revolution and of industrial transformation. 

An ever-increasing number of connected Internet-of-thing (IoT) devices now collect data, requiring at the edge more storage and computational capacity and more intelligence. The IoT-edge partnership expects to revolutionize data computing, with various gains for those looking to leverage and harness the power of data analytics when developing solutions for major industry verticals. One of the most important edge applications with a huge potential societal impact involves biomedical devices such as medical implants (e.g. for epilepsy early detection).

Today‚Äôs AI solutions are mainly deployed in the cloud, as they are extremely power hungry, and are unsuitable for energy-constrained IoT-edge devices. Deploying AI at the edge requires new computing engines with energy efficiencies 100-1,000x better than current state-of-the-art technologies. 

The SELF Lab targets the design and development of smart edge computing engines. We demonstrate their superiority for personalised healthcare such as early epilepsy detection (a neurological disease that manifests as a brain-wide phenomenon). The computing engine will be based on computation-in-memory architecture, going beyond traditional Von-Neumann. It will make use of memristor devices, which are well suited to brain-inspired computing, combined with new biological inspired learning algorithms and power-aware efficient mapping methods.

The SELF Lab is part of the TU Delft AI Labs programme.

The Team