Neurally-plausible radial basis kernels using distributed Fourier embeddings
For computational neuroscience and AI researchers seeking biologically plausible distributed representations, this work provides a theoretical analysis linking grid cell codes to radial basis kernels.
The paper characterizes radial basis kernels realizable in the neurally-plausible framework of spatial semantic pointers, showing that grid cell-like representations are both capable of and optimal for realizing these kernels.
Coherent, continuous spatial representations are critical for synthesizing physical and perceptual phenomena into a single representational space. Radial basis kernels provide a path forward for this type of distributed representation. In this work, we aim to characterize and analyze common radial basis kernels realizable in the neurally-plausible framework of spatial semantic pointers. Further, we analyze previous radial basis kernel work based on grid cell-like representations and demonstrate that such representations are both capable of and optimal for realizing radial basis kernels.