David Carlson
Papers
1
Total Citations
12
H-Index
1
About
David Carlson is a leading researcher at the intersection of machine learning and computational neuroscience, with a primary focus on developing algorithms for brain-computer interfaces (BCIs) and neural data analysis. His most cited work, "Neuroprosthetic Decoder Training as Imitation Learning" (2016, 12 citations), redefines how neuroprosthetic decoders are trained by framing the process as an imitation learning problem. This insight allows BCIs to adapt more naturally to a user’s neural signals, improving the fluidity and accuracy of cursor or robotic arm control. Beyond this contribution, Carlson’s research explores how statistical machine learning—particularly Bayesian nonparametrics and latent variable models—can uncover hidden structure in high-dimensional neural recordings. His work has direct implications for restoring motor function in paralyzed patients and for understanding how neural populations encode behavior. By bridging theoretical rigor with practical neuroengineering challenges, Carlson has established himself as a key figure in the push toward more intelligent, adaptive neural prosthetics that learn alongside their users.
Research Focus
Key Achievements
Top Papers
- 1Neuroprosthetic Decoder Training as Imitation Learning12 citations · 2016