AI Enhances Visual Cortical Prosthesis Research at UCSB

Researchers from the University of California, Santa Barbara, ETH Zurich and Miguel Hernández University have shown that a deep‑learning model can design precise electrical‑stimulation patterns for electrodes temporarily implanted in the visual cortex of a blind participant. The model improved control over neuronal responses and helped predict the participant’s visual perception, marking a proof‑of‑concept step toward more accurate visual cortical prostheses.

The study, published in the journal *Neuron*, was led by co‑first authors Pehuén Moure (ETH Zurich), Jacob Granley (UCSB) and Fabrizio Grani (Miguel Hernández University), with supervision from Michael Beyeler, Shih‑Chii Liu and Eduardo Fernández. It forms part of a broader feasibility trial in Spain and could eventually benefit people whose visual pathways are damaged but whose visual cortex remains functional, such as those blinded by strokes, neurodegenerative disease or injury.