Delft AI Lab Lunch with DeTAIL & SELF Lab

About DeTAIL

The Delft Tensor AI Lab

Undoubtedly, we live in the era of big data. Real life data - in the biomedical field and beyond - often comes high-dimensional. Current signal processing solutions artificially segment such high-dimensional data into shorter one- or two-dimensional arrays, causing information loss by destroying correlations between these data. At the same time, advances in (biomedical) sensor and imaging technology – such as substantially larger recording durations of wearable sensor technology or the unprecedented increase in spatial and temporal resolution of the latest neuroimaging techniques – have led to ever increasing data sets. Tensors (multi-dimensional arrays) are the data structure of choice in artificial intelligence research to exploit the full potential of these data in a timely manner.

Within the DeTAIL Lab, we focus on both the development of novel low-rank tensor methods and their application for biomedical signal processing, thereby enabling a much faster, and therefore more energy-sustainable, training of AI models from large datasets without any loss of accuracy.

About SELF Lab

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 industrial transformation. The rise of connected Internet-of-Things (IoT) devices has led to increasing data collection, which requires greater storage, computational power, and intelligence at the edge. This partnership between IoT and edge computing has the potential to transform data computing and yield significant benefits for industry verticals. Among the crucial edge applications, biomedical devices such as medical implants (e.g., for epilepsy early detection) have enormous potential societal impact. Another exciting application of edge computing is the neuromorphic control of soft robots, which can benefit from advanced computational capabilities at the edge to achieve highly adaptable and responsive behavior, making them suitable for medical, industrial, and environmental applications.

Today’s AI solutions 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 of 100 to 1000 times 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 personalized 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, beyond traditional Von-Neumann. It will use memristor devices well suited to brain-inspired computing, combined with new biologically inspired learning algorithms and power-aware efficient mapping methods.