R
Reza Shahbazi
Researcher at Cornell University
Publications - 14
Citations - 86
Reza Shahbazi is an academic researcher from Cornell University. The author has contributed to research in topics: Cushion & Drop (telecommunication). The author has an hindex of 4, co-authored 9 publications receiving 72 citations. Previous affiliations of Reza Shahbazi include University of California, San Diego.
Papers
More filters
Journal ArticleDOI
Renewing the respect for similarity
Shimon Edelman,Reza Shahbazi +1 more
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.
Journal ArticleDOI
Similarity, kernels, and the fundamental constraints on cognition
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.
Hemispheric Asymmetry in Visual Perception Arises from Differential Encoding Beyond the Sensory Level
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.
Dissertation
Structure And Similarity In Vision
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.
Journal ArticleDOI
Survival in a world of probable objects: A fundamental reason for Bayesian enlightenment
Shimon Edelman,Reza Shahbazi +1 more
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.