Presentation 1:
Speaker: Shobhit Jagga, 3rd Year UG Student Department of Computer Science & Engineering
Title: The Role of Reward Dimensions in Preference Reversal
Type: Own Project
Abstract: Previous studies has shown that in contrast to rational choice theory human subjects fail to maximize by exhibiting melioration where they prefer smaller sooner reward over larger later reward and also exhibit time-inconsistent preferences. The presented study aims to find out the sensitivity of such preferences to reward dimensions to find out what changes in reward dimensions result in preference reversal where the larger later reward is preferred over smaller sooner reward.
Slides: pptx pdf
Links to Look at:
Presentation 2:
Speaker: Shashi Kant, Final Year UG Student Department of Electrical Engineering
Title: IVSN: A Biologically Inspired Computational Model for Visual Search
Type: Paper
Paper: Zhang, M., Feng, J., Ma, K.T. et al. Finding any Waldo with zero-shot invariant and efficient visual search. Nat Commun 9, 3730 (2018)
Abstract: Searching for a target object in a cluttered scene constitutes a fundamental challenge in daily vision. The visual search must be selective enough to discriminate the target from distractors, invariant to changes in the appearance of the target, efficient to avoid exhaustive exploration of the image, and must generalize to locate novel target objects with zero-shot training. Previous work on visual search has focused on searching for perfect matches of a target after extensive category-specific training. Here, they show for the first time that humans can efficiently and invariantly search for natural objects in complex scenes. To gain insight into the mechanisms that guide the visual search, they propose a biologically inspired computational model that can locate targets without exhaustive sampling and which can generalize to novel objects. (Abstract taken as it is from the original paper)
Slides: pptx pdf
Links to Look at: