July 28, 2025
The GIST Curved neural networks enable AI memory recall through geometric design 
Gaby Clark
scientific editor
Andrew Zinin
lead editor
Editors' notes
This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:
fact-checked
peer-reviewed publication
trusted source
proofread
A new international study has introduced Curved Neural Networks—a new type of AI memory architecture inspired by ideas from geometry. The study shows that bending the "space" in which AI "thinks" can create explosive memory recall—an effect similar to a lightbulb moment in the human brain. The research opens new paths for brain-inspired computing, neuroscience, and even next-gen robotics, offering tools to better understand memory itself.
What if artificial intelligence could remember things not just well, but faster or more reliably? A new international study has introduced a novel type of AI memory—one that addresses the challenge not with more data, but with geometry.
A team of researchers from the Basque Center for Applied Mathematics (BCAM), Araya Inc., the University of Sussex, and Kyoto University has developed a new class of AI models called Curved Neural Networks.
Their findings, published in Nature Communications, show how bending the "space" in which AI "thinks" can create explosive memory recall—an effect similar to a lightbulb moment in the human brain.
Traditional AI systems rely on relatively simple connections—akin to one-on-one conversations. "But the human brain operates with rich, multi-way interactions, where many signals influence each other at once," said Miguel Aguilera at BCAM. To account for this, the team introduced curved geometry into AI models, allowing for more complex and lifelike memory processes—without extra computational overload.
The team's Curved Neural Networks revealed three key features: Explosive Memory Recall, in which the system can readily jump to a stored memory, like flipping a switch; Self-Tuning Intelligence, in which the AI automatically adjusts its "focus" as it recalls, speeding up its response; and Fewer Mistakes, in which a single tuning parameter lets the system balance between memory power and accuracy.
"These properties are not hardcoded, but arise naturally from the curved geometry of the model," said Pablo A Morales at Araya Inc. This discovery could lead to AI systems that are more adaptive, efficient, and easier to understand—a major leap from today's "black box" models that are powerful but hard to explain.
"It's a compelling example of how geometry and physics can guide advances in intelligence—both natural and artificial," said University of Sussex's Fernando E. Rosas. "This work opens new ways of thinking about how brains and machines may store and retrieve information efficiently."
Hideaki Shimazaki, associate professor at Kyoto University, added, "What started as a simple idea—using curved geometry in neural networks—unfolded into a deeply collaborative journey. The discovery will undoubtedly contribute to the future of AI."
More information: Miguel Aguilera et al, Explosive neural networks via higher-order interactions in curved statistical manifolds, Nature Communications (2025). DOI: 10.1038/s41467-025-61475-w
Journal information: Nature Communications Provided by Kyoto University Citation: Curved neural networks enable AI memory recall through geometric design (2025, July 28) retrieved 28 July 2025 from https://techxplore.com/news/2025-07-neural-networks-enable-ai-memory.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
Explore further
Balanced excitatory and inhibitory neurons help brain networks store and process memories 0 shares
Feedback to editors
