The brain generates activity in the form of oscillations. Brain waves span from very slow rhythms, typical of sleep, to faster oscillations during attention and cognitive processing. Moreover, changes of brain oscillations are markers of some neurological diseases. Given the dynamism of brain activity, these events are far from stationary and thus their identification in real time is a daunting task.
NeuroCONVO is a research project from the Laboratorio de Circuitos Neuronales at the Instituto Cajal, CSIC (http://hippo-circuitlab.es/) aiming to apply convolutional neural networks to identify specific types of brain waves using data from high-density intracranial recordings.
Different network architectures are trained to optimize the recognition of brain waves for application in neuroscience research. Tuning different sets of parameters provides an appropriate balance between false and true detection of a number of labeled events. Some NeuroCONVO networks are able to predict the emergence of oscillations in advance.
By enabling detection of brain oscillations in real time, NeuroCONVO looks to improve our ability to decipher brain dynamics in health and disease.