This meeting examines how brain-inspired hardware could reduce AI’s growing energy requirements. Researchers connect materials and memory devices with circuits, systems and applications, including sparse computation and compute-in-memory architectures that reduce data movement. Two discussion days address fundamental advances and challenges; the final day considers translation and wider impacts. Programme participants include Steve Furber, Judith Driscoll and Tony Kenyon. The meeting takes place at The Royal Society, 6–9 Carlton House Terrace, London SW1Y 5AG, or online, on 23–25 November 202