LIVE
Pedestal AI Secures Seed Funding to Automate Logistics With Intelligent Agents United Launch Alliance Investigates Vulcan Rocket Failure US Southwest Hydropower Output Hits Record Lows Amid Persistent Drought YouTube Updates View Metrics to Include TV Co-Viewing Estimates OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States Pedestal AI Secures Seed Funding to Automate Logistics With Intelligent Agents United Launch Alliance Investigates Vulcan Rocket Failure US Southwest Hydropower Output Hits Record Lows Amid Persistent Drought YouTube Updates View Metrics to Include TV Co-Viewing Estimates OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States

AI-Powered Visual Prosthesis Breakthrough Aims to Restore Sight

🤖 AI Models 2 min read 👁 3

Researchers have demonstrated that deep learning can significantly improve the precision of brain implants designed to restore vision in blind individuals. The proof-of-concept study showcases how AI adapts electrical stimulation to match individual neural responses.

AI-Powered Visual Prosthesis Breakthrough Aims to Restore Sight🤖AI Models

Photo: ScienceDaily AI

Key points

  • Researchers used a deep learning system to improve brain implant precision for the blind.
  • Clinical testing took place in Spain with a patient fitted with a visual cortex electrode array.
  • The AI model adapts to individual brain responses to make visual sensations more predictable.

An international team of researchers, including scientists from UC Santa Barbara, has successfully tested a deep learning system designed to overcome major hurdles in developing bionic eyes. By analyzing neural responses, the artificial intelligence model helps predict how the visual cortex reacts to electrical stimulation, allowing for more consistent visual sensations known as phosphenes.

Traditional visual prostheses often struggle to produce reliable results because identical electrical impulses do not always trigger the same perception. To address this inconsistency, the team deployed a deep neural network that factors in the brain's resting activity immediately prior to stimulation. The technology was evaluated during clinical testing in 2024 at Hospital IMED Elche in Spain, where researchers worked with a 27-year-old man who lost his sight due to a traumatic brain injury and was fitted with a 96-electrode cortical array.

Unlike devices that target the retina or optic nerve, cortical prostheses deliver electrical signals directly to the visual cortex at the back of the brain. This alternative approach offers potential hope for patients whose visual pathways are damaged from strokes, trauma, or neurodegenerative diseases, provided their visual cortex remains responsive. The research builds upon foundational computational work backed by a National Institutes of Health Director's New Innovator Award.

Building a model in the abstract is one thing. Seeing it shape an experiment with a person is something else entirely. — Michael Beyeler, UC Santa Barbara

What to watch next: Future trials will test whether these adaptive AI models can maintain long-term reliability and help patients interpret more complex visual shapes and patterns.

Source ScienceDaily AI — sciencedaily.com/releases/2026/11/261110042553.htm ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.