Generative adversarial neural networks maintain decoder accuracy during signal disruption in simulated long-term recordings from brain computer interfaces
Thomas Stephens, Jon Cafaro, Ryan MacRae, Stephen Simons
This paper presents a GAN-based method to recover degraded signals in simulated long-term BCIs, maintaining decoder accuracy despite signal disruption.
bioRxiv · May 18, 2021 · PreprintNeuroscience