Memristive Networks Learn by Reorganizing: When the Material Is the Model

bravo_abad · x · 2026-09-20

In a post on his AI-for-Science newsletter Discovery at Scale, researcher Jorge Bravo Abad argues for a radical alternative to conventional AI hardware: instead of running a neural-network algorithm more efficiently on the material, let self-organizing memristive networks use the material's own dynamics as the computation itself.

These systems are random networks of nanowires or nanoparticles that learn by physically reorganizing themselves under electrical stimulation, embodying the model directly in hardware. The author frames this within his broader theme of making scientific discovery more systematic, scalable, and repeatable.

Related event: Memristive Networks Turn the Material Itself into the Model(2 posts)→

Original post →

More from Research

Research channel →