Scientists at Kobe University have developed an AI algorithm that can accurately predict a mouse's movement based on brain imaging data with 95% accuracy. The deep learning algorithm requires no data preprocessing and can generate predictions based on just 0. 17 seconds of imaging data. The researchers also developed a technique to identify the key parts of the data that contributed to the predictions, providing insights into the AI's decision-making process.

This advancement could revolutionize brain-machine interface technology and help develop non-invasive, real-time interfaces. The study was funded by various organizations, including the Japan Society for the Promotion of Science and the Japan Agency for Medical Research and Development.