According to an international team of researchers, the power consumption of artificial intelligence is set to double by 2026. However, they have presented a roadmap for brain-inspired computing technology that could significantly reduce AI’s environmental impact while enhancing its capabilities.
The team’s comprehensive review, published on January 22 in Nature by 23 experts from academia and industry, outlines how neuromorphic computing, which mimics the brain’s architecture, could transform various sectors using a fraction of the energy consumed by conventional systems.
Professor Gert Cauwenberghs, from UC San Diego’s Department of Bioengineering and one of the coauthors of the paper, highlights the importance of neuromorphic computing in addressing the escalating power demands of AI systems.
Dhireesha Kudithipudi, the Robert F. McDermott Endowed Chair at the University of Texas San Antonio and the corresponding author of the paper, states that there is a significant opportunity to develop new architectures and frameworks for commercial applications now.
The applications of neuromorphic computing are diverse, ranging from scientific computing and AI to augmented reality, wearable tech, smart agriculture, and urban infrastructure. Recent advancements have shown promise in reducing energy consumption while maintaining accuracy in AI applications.
To achieve widespread adoption, the researchers suggest that neuromorphic systems should replicate the brain’s selective pruning of neural connections, optimizing spatial efficiency and information retention.
The roadmap emphasizes the need for collaboration between academia and industry to develop user-friendly programming tools for broader accessibility. They propose a range of hardware designs tailored to different applications to accelerate adoption across various sectors.
Progress is already in motion, with Cauwenberghs and Kudithipudi securing funding for THOR: The Neuromorphic Commons, a research network aimed at advancing neuromorphic computing through collaborative innovation.
If you found this piece useful, please consider supporting our work with a small, one-time or monthly donation. Your contribution enables us to continue bringing you accurate, thought-provoking science and medical news that you can trust. Independent reporting takes time, effort, and resources, and your support makes it possible for us to keep exploring the stories that matter to you. Together, we can ensure that important discoveries and developments reach the people who need them most.
