Phase-transition 2D memristor achieves ultrafast/ energy-efficient switching for AI accelerators, edge computing, and neuromorphic networks

https://www.eurekalert.org/news-releases/1080271

"Cu+ ion natural migration within Cu2S enables monoclinic-tetragonal phase transition at extremely low energy costs, scalable... memristor overcomes crystal damage, high power consumption, limited endurance... vacancy formation energy in Cu2S only 0.188 eV, order magnitude lower... record-low 1 μW at 100 mV SET power consumption, 80 ns  response time, withstands >400 cycles under DC sweep/ 500 cycles under pulse testing... implemented in simulated crossbar array for image processing... gesture recognition"

Related:

How can AI be more energy efficient? Researchers look to human brain for inspiration
https://techxplore.com/news/2025-07-ai-energy-efficient-human-brain.html

Exploring scalable pathways for cost-effective memristors using solution-processed 2D materials
https://www.eurekalert.org/news-releases/1089702

Liquid droplets trained to play tic-tac-toe
https://phys.org/news/2025-07-liquid-droplets-play-tic-tac.html

Scientist discusses development of artificial synapses that mimic human brain function for next-gen AI chips
https://techxplore.com/news/2025-09-scientist-discusses-artificial-synapses-mimic.html