Photo: Michael Veit / BCF
In football, one decisive element of the game is finding the right balance between offense and defense. While seeking to score as many goals as possible, it is just as important to intercept counterattacks of the opposing team. A similar trade-off can occur in the stimulation of neuronal networks where a stimulus interacts with the inherent activity of the networks and the efficacy of the stimulation depends on the timing.
Sreedhar Saseendran Kumar and his co-authors have approached the question if the optimal timing can be determined automatically for each network. With the help of “reinforcement learning“, a machine learning strategy, the stimulation of a network could be progressively optimized by trial and error and a outcome-based reward system. Kumar’s study was a collaboration between scientists from the IMTEK, the Bernstein Center Freiburg and the Machine Learning Lab at the Department of Computer Science. It was made possible thanks to fundings by BrainLinks-BrainTools and has recently been published in the scientific journal PLoS Computational Biology.
Original publication: