AI RESEARCH
Beyond Activation Alignment: The Geometry of Neural Sensitivity
arXiv CS.LG
•
ArXi:2605.03222v1 Announce Type: new Activation-alignment measures such as Representational Similarity Analysis (RSA), Canonical Correlation Analysis (CCA), and Centered Kernel Alignment (CKA) are widely used to compare biological and artificial neural representations. Recent theoretical work interprets many of these methods as assessing agreement between optimal linear readouts over broad families of global tasks. However, agreement at the level of global readouts does not determine how a system uses local stimulus evidence.