Artificial Intelligence (AI) tasks on digital von Neumann hardware causes an unprecedented amount of data flow between memory and processor. This is seriously challenging the conventional computation hardware in terms of speed and power consumption. Therefore, biologically inspired neuromorphic computing systems based on emerging memory devices, which combine storage and processing, are emerging as a viable solution. However, sustainable material based hardware development is often time consuming and expensive. The AI4AI project aims towards an AI based material design strategy for developing neuromorphic AI hardware that will be capable of performing AI tasks while operating at an extremely low power consumption in the order of fJ/bit. The research will demonstrate development of new hardware to bring neuromorphic computing to a level where proof-of-concept system demonstrates an ultra-low power operation without compromising the computational speed, accuracy, or learning capacity.

2023

2025