NWO grant for UM research into deep learning

The last ten research projects for NGF AINED XS Europe were launched via NWO. These grants enable research on promising ideas and innovative or challenging initiatives in the field of Artificial Intelligence (AI). The projects range from AI applications in cancer diagnosis, to robotic arms, and underwater communication of satellites. These granted projects are performed in collaboration with at least one foreign European collaborative partner organisation.

Guangzhi Tang, Assistant Professor, Faculty of Science and Engineering, Department of Advanced Computing Sciences at Maastricht University receives a grant for his project Brain-inspired MatMul-free Deep Learning for Sustainable AI on Neuromorphic Processor.

Sustainable and accessible AI

Deep learning depends on energy-intensive matrix multiplication (MatMul) computations on GPUs, which become unsustainable as neural networks scale up. Inspired by the brain's efficient use of asynchronous and local computations, this project aims to develop a new computing paradigm for deep learning that reduces energy consumption and latency, shifting away from traditional GPU-based MatMul. Collaborating with researchers at TU Dresden in Germany, Tang and his colleagues plan to implement this brain-inspired computing paradigm on neuromorphic processors and integrate it into generalized tools. This approach has the potential to make AI more sustainable and accessible for large-scale applications, reducing energy costs and environmental impacts.

Also read