Curved neural networks bend space in which AI thinks, enabling it to remember not just well, but also faster and more reliably

https://techxplore.com/news/2025-07-neural-networks-enable-ai-memory.html

"not by using more data or computational overload, but with geometry... self-tuning intelligent AI automatically adjusts focus as it recalls, speeding up its response; with fewer mistakes, single tuning parameter lets system balance between memory power/ accuracy... properties not hardcoded, but arise naturally from curved geometry... more adaptive, efficient, easier to understand, instead of black box models that are powerful but hard to explain... brain-inspired computing, neuroscience, robotics"

Related:

Brain-inspired AI architecture could computing faster and far less power-hungry
https://techxplore.com/news/2026-06-brain-ai-architecture-faster-power.html

“Scan the map first, then zoom in”: DGIST develops radar technology for autonomous robots that reduces computational load by 88%
https://www.eurekalert.org/news-releases/1144918

Taming heat at the nanoscale to satiate energy-hungry artificial intelligence
https://www.eurekalert.org/news-releases/1144640