Add to Favourites
To login click here
Meta Platforms, Inc. has announced Image Decoder, a new deep learning application based on Meta’s open source foundation model DINOv2. This application translates brain activity into highly accurate images of what the subject is looking at or thinking of nearly in realtime. The technology behind Image Decoder combines two fields: machine learning and neuroscience, and was developed by researchers at the Facebook Artificial Intelligence Research lab (FAIR) and PSL University in Paris. This research strengthens Meta’s long-term research initiative to understand the foundations of human intelligence and build AI systems that can learn and reason like humans.
