This latest deep learning algorithm can analyse brain scans to predict thoughts. Deep learning neural networks seemingly become more impressive and complex every day and now some scientists are pushing the capabilities of these algorithms to a whole new level, they are trying to use them to read minds.
By reverse-engineering signals sent by the brain, researchers at Carnegie Mellon University have been working on an AI that can read complex thoughts by simply looking at brain scans. Using the data collected from a functional MRI machine, the CMU scientists feed that data into their machine learning algorithms that can locate the building blocks that the brain uses to create these complex thoughts.
The team were able to demonstrate where and how the brain was being triggered while processing 240 complex events, covering everything from individuals to places and even various physical actions of social interaction. Selecting 239 of these complex sentences and feeding the AI the corresponding brain scans, the algorithm managed to successfully predict the correct thoughts with an astounding 87 percent accuracy. It could also do the reverse, receiving a sentence and then outputting an accurate image of how it predicted that thought would be mapped inside a human brain.
This just shows you how far AI has come, and it is thoroughly exciting if you think what else will be done in the near future.