Reza Shahbazi

TL;DR: It is argued for a renewed focus on similarity as an explanatory concept, by surveying established results and new developments in the theory and methods of similarity-preserving associative lookup and dimensionality reduction—critical components of many cognitive functions, as well as of intelligent data management in computer vision.

TL;DR: It is argued that kernel-like neural computation is particularly suited to serving such learning and decision making needs, while simultaneously satisfying four fundamental constraints that apply to any cognitive system that is charged with learning from the statistics of its world.

TL;DR: Hsiao et al. as discussed by the authors used two autoencoder networks with differential connectivity configurations as the way to develop differential encoding in the two hemispheres, to reflect the anatomical evidence that there is more interconnectivity among the neighboring cortical columns in the right hemisphere than the left hemisphere.

TL;DR: A behavioral experiment to investigate the effect of the degree of hierarchy of the generative probabilistic structure in categorization and suggests that participants perform more accurately in the case of hierarchically structured stimuli.

TL;DR: The only viable formulation of perception, thinking, and action under uncertainty is statistical inference, and the normative way of statistical inference is Bayesian as mentioned in this paper, which is why even seemingly non-Bayesian computational frameworks in cognitive science ultimately draw their justification from Bayesian considerations.