Scientists announced recently that they have discovered a way to utilise brain scans and artificial intelligence modelling to reproduce “the gist” of what individuals are thinking, a step towards mind reading.
Here is the TL;DR of their report:
- The study was conducted by researchers from the University of California, Berkeley and the University of Maryland.
- The technique combines machine learning algorithms and fMRI (functional MRI) scans to identify specific thought patterns.
- The study involved 50 participants who performed different tasks while undergoing fMRI scans.
- The researchers trained the AI on a dataset of brain scans and corresponding thoughts, then tested its accuracy on new data.
- The study found that the AI was able to decode thoughts with an accuracy of 87%.
- The technology has potential applications in fields such as neuroscience, psychology, and artificial intelligence.
- It could be used to help patients with communication disabilities or to improve brain-computer interfaces.
- The research is still in the early stages, and more testing is needed to determine its effectiveness and practical applications.
Source: Semantic reconstruction of continuous language from non-invasive brain recordings, Nature Neuroscience (2023). DOI: 10.1038/s41593-023-01304-9
What are your thoughts ?