The temporal convolutional network (TCN) remained the strongest forecasting model that achieved in the majority of testing scenarios 90% rhythm's envelope correlation with 10 ms effective delay and circular standard deviation of phase estimates. We compared it against the state-of-the-art techniques using synthetic and real data from 25 subjects. The strongest architecture was then trained to simultaneously filter and forecast EEG data. We tested five neural networks with conceptually distinct architectures in forecasting synthetic EEG rhythms.
#CONTEXT REINSTATEMENT ENCODING SPECIFICITY PRINCIPLE SERIES#
Given the high quality of modern time series forecasting neural networks we explored their utility for low-latency extraction of brain rhythm parameters. To some extent they can be compensated using forecasting models. Isolating narrow-band signals incurs fundamental delays. Novel more efficient approaches capable of tracking brain rhythm's phase and envelope are needed for scenarios that entail instantaneous interaction with the brain circuits. Lower delay between neuronal events and the appropriate feedback increases the efficacy of such interaction. This requires interpreting brain's rhythmic activity and generating timely feedback to the brain. Neurofeedback and brain-computer interfacing technology open the exciting opportunity for establishing interactive closed-loop real-time communication with the human brain.
0 kommentar(er)
