Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks

arXiv:2405.01012v1 Announce Type: cross
Abstract: Centred Kernel Alignment (CKA) has recently emerged as a popular metric to compare activations from biological and artificial neural networks (ANNs) in order to quantify the alignment between internal representations derived from stimuli sets (e.g. images, text, video) that are presented to both systems. In this paper we highlight issues that the community should take into account if using CKA as an alignment metric with neural data. Neural data are in the low-data high-dimensionality domain, …

abstract alignment anns artificial artificial neural networks arxiv cka cs.cv images kernel networks neural networks popular q-bio.nc text type video