Spikernels: Predicting Arm Movements by Embedding Population Spike Rate Patterns in Inner-Product Spaces
Published in Neural Computation, 2005
Developed Spikernels, biologically motivated kernels for cortical activity modeling. Demonstrated their effectiveness in predicting arm movements from neural population spike counts, outperforming standard scalar products.
Recommended citation: Shpigelman et al (2005). "Spikernels: Predicting Arm Movements by Embedding Population Spike Rate Patterns in Inner-Product Spaces." Neural Computation.
Download Paper