MEGIN Spotlights podcast

Brain2Qwerty – Decoding Brain Activity with MEG and AI

0:00
9:46
Reculer de 15 secondes
Avancer de 15 secondes

What if typed sentences could be decoded from human brain activity?

In this MEGIN Spotlight, Nicole Brough is joined by Jean-Remi King, CNRS researcher and leader of the Brain and AI team at Meta AI, to discuss the Brain2Qwerty research project. The team are investigating how MEG can record brain activity while people type, and how AI can interpret these signals to generate written language. Jean-Remi discusses the motivation behind the research, why MEG was chosen, and how Brain2Qwerty has evolved from V1 to V2, incorporating larger datasets and newer AI approaches.

Learn more: From Brain Waves to Words: Brain2Qwerty Offers a New Path to Communication Without Surgery: https://ai.meta.com/blog/brain2qwerty-brain-ai-human-communication/

Read more about Brain2Qwerty V1: https://ai.meta.com/research/publications/brain-to-text-decoding-a-non-invasive-approach-via-typing/?utm_source=linkedin&utm_medium=organic_social&utm_content=video&utm_campaign=fair

Read more about Brain2Qwerty V2:  https://ai.meta.com/research/publications/accurate-decoding-of-natural-sentences-from-non-invasive-brain-recordings/

#MEGIN #MEG #Brain2Qwerty #Neuroscience #ArtificialIntelligence #BrainComputerInterfaces #Neurotechnology

Don't forget to like and subscribe for more conversations at the forefront of brain science.

 

MEGIN Spotlights content and speakers selected are only for information purposes and MEGIN does not endorse any applications or treatments mentioned.

This presentation does not constitute any form of medical opinion or professional advice. Consult your caregiver for medical advice. TRIUX™ neo is intended to non-invasively record brain activity, and when interpreted by trained physicians, to help localize these active areas. Caution: Federal law (USA) restricts this device to sale by or on the order of a physician.

D'autres épisodes de "MEGIN Spotlights"