Tiny quantum nanostructures could make AI less of an energy hog
Engineers at the University of Wisconsin–Madison have designed a new type of quantum nanostructure that could enable optical neural networks. This emerging technology has the potential to make artificial intelligence systems, like large language models and image generation, faster and significantly more energy efficient.
Engineers at the University of Wisconsin–Madison have developed a novel quantum nanostructure that could make optical neural networks more energy-efficient. This breakthrough could lead to faster and more sustainable artificial intelligence systems, such as large language models and image generators. Optical neural networks, which use light instead of electricity, have the potential to significantly reduce AI's energy consumption.
However, they currently lack nonlinearity, a crucial property that enables AI systems to learn complex patterns. Researchers led by Qingyi Zhou and Jungmin Kim set out to overcome this limitation by exploring quantum emitters, materials known for their strong optical nonlinearity. By designing a nanostructure around a quantum emitter, the team was able to achieve the necessary nonlinearity for optical neural networks.
Their simulations indicate that this approach could reduce power consumption by seven orders of magnitude compared to existing optical materials. While the results are theoretical, the researchers believe that current technology could make this quantum-based optical neural network a reality.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
