Here we show one application of machine learning and signal processing in Neuroscience; translating thoughts into actions with our Game-Based Brain-Computer interface (BCI).
BCI enables direct control of brain activity over external devices such as robots. Motor imagery (MI) based BCIs detect changes in brain activity associated with imaginary limb movements, such as grasping with the right or left hand. MI based BCIs require training, during which the user gradually learns how to control the relevant patterns of brain activity with the help of feedback. Additionally, it is common to use machine learning techniques to improve BCI performance and adapt the decoding algorithm to the user’s brain. Therefore, the brain and the BCI need to “collaborate” in order to constantly improve performance.
BCI is not science fiction, but a complete machine learning pipeline between a brain and a specific end point. It can be used for communication, rehabilitation, control, diagnosis and gaming.
