A hardware-software co-design can efficiently run AI on edge devices

Дата публикации: 11-04-2026 15:00:04

A new hardware-software co-design increases AI energy efficiency and reduces latency, enabling real-time processing of continuous data streams like video or sensor feeds. The neuromorphic approach unlocks the ability to run powerful, real-time AI directly on local edge devices like phones, hearing aids or autonomous vehicle cameras, according to a University of Michigan Engineering study published in Nature Communications.

Основное содержимое страницы с новостью.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Engineers make edge AI more efficient by redesigning both algorithm and hardware	0	6.77	17-08-2026
2	Cornell engineers use tiny vibrating beams to rethink AI hardware	0	8.98	01-06-2026
3	Edge AI, Not Cloud AI, to Define the Next Generation of Autonomous Vehicles: NXP	0	8.24	05-08-2026
4	Magnetic memory could make edge AI faster while reducing energy use	0	8.1	28-08-2026
5	Японские ученые представили 3D-архитектуру для энергоэффективных AI-чипов высокой точности	0	0	15-06-2020
6	Forget electrons, this breakthrough uses light-matter particles to power AI	0	16.53	19-05-2026
7	AI in battlefield intelligence: Expanding the speed of decision-making	5	7	10-07-2026
8	Hardware-aware framework accelerates large language models without additional training	0	8.57	06-08-2026
9	Brain-inspired nanopore device uses current-induced heating for memory operations	0	7	16-07-2026
10	Quantum sensing microscope illuminates transistor design	0	7.23	21-07-2026

Классификация: Наука. Схожих патентов: 0. Схожих новостей: 10. Тональность: 5. Информативность: 7. Источник: phys.org.