← Search

Ariel Telpaz

2 accepted papers

2022

From Bottom-Up To Top-Down: Characterization Of Training Process In Gaze Modeling

ICASSP 2022accepted

During training, artificial neural networks might not converge to a global minimum. Usually, using gradient descent, the training procedure cause the network to stroll in the high-dimensional weights’ space. This stroll passes adjacently to local minima and locations in the geometry of loss landscap…

Cited by 0SourceScholar
2019

Information Constrained Control for Visual Detection of Important Areas

ICASSP 2019accepted

In this work, we propose a method for detection of locations with subjective significance in the visual environment using Information Constrained Control (ICC). ICC is a model that takes into consideration not only the goal but also the complexity of the control needed to achieve it, characterized b…

Cited by 0SourceScholar