Topic: Fisher information matrix

Similarity between neural representations is often quantified by measuring alignment of the representations over a set of natural stimuli that are relatively far apart in stimulus space (Kriegeskorte et al. 2008). However, systems with similar global structure can have strikingly different sensitivities to local stimulus distortions (Szegedy et al. 2013), suggesting a need for metrics that compare local sensitivities of representations. We propose a framework for comparing a set of image representations in terms of their sensitivities to local distortions. We quantify the local geometry of a r