Publications by authors named "Bareesh Bhaduri"
Article Synopsis
- Current intracortical brain-computer interfaces (iBCIs) primarily use spiking data for decoding neural activity, which can be accurate but requires high sampling rates that can be challenging to maintain.
- An alternative approach involves using local field potentials (LFPs) to capture continuous signals alongside spikes, but LFPs alone have not matched the performance of spike-based decoding.
- This study shows that by training models to use LFPs to predict firing rates from spiking data, the performance can improve significantly, allowing for lower power iBCI devices that still achieve high accuracy, even outperforming direct spike decoding in many cases.
Artificial neural networks (ANNs) are state-of-the-art tools for modeling and decoding neural activity, but deploying them in closed-loop experiments with tight timing constraints is challenging due to their limited support in existing real-time frameworks. Researchers need a platform that fully supports high-level languages for running ANNs (e.g.
View Article and Find Full Text PDFArtificial neural networks (ANNs) are state-of-the-art tools for modeling and decoding neural activity, but deploying them in closed-loop experiments with tight timing constraints is challenging due to their limited support in existing real-time frameworks. Researchers need a platform that fully supports high-level languages for running ANNs (e.g.
View Article and Find Full Text PDF