Research Article
A Tensor-Product-Kernel Framework for Multiscale Neural Activity Decoding and Control
Algorithm 1
Quantized kernel least mean square (QKLMS) algorithm.
Input: | Initialization: initialize the weight vector : codebook (set of centers) and coefficient vector | Computation: | For | (1) compute the output | | (2) compute the error, | (3) compute the minimum distance in RKHS between and each , | | (4) if , then keep the codebook unchanged: , and update the coefficient of the center closest to : | , where | (5) otherwise, store the new center: , | (6) | end |
|