output
20162023
most citedPhysics-informed data based neural networks for two-dimensional turbulence

63 citations

Showing 2020Show all

7 papers · 1 filter

cs.RO2020

Multi-Instance Aware Localization for End-to-End Imitation Learning

Sagar Gubbi Venkatesh, Raviteja Upadrashta, Shishir Kolathaya +1

Existing architectures for imitation learning using image-to-action policy networks perform poorly when presented with an input image containing multiple instances of the object of…

cs.RO202018 cited

Imitation Learning for High Precision Peg-in-Hole Tasks

Sagar Gubbi, Shishir Kolathaya, Bharadwaj Amrutur

Industrial robot manipulators are not able to match the precision and speed with which humans are able to execute contact rich tasks even to this day. Therefore, as a means overcom…

cs.RO20205 cited

Teaching Robots Novel Objects by Pointing at Them

Sagar Gubbi Venkatesh, Raviteja Upadrashta, Shishir Kolathaya +1

Robots that must operate in novel environments and collaborate with humans must be capable of acquiring new knowledge from human experts during operation. We propose teaching a rob…

cs.LG2020

Convergence Analysis of Homotopy-SGD for non-convex optimization

Matilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh +2

First-order stochastic methods for solving large-scale non-convex optimization problems are widely used in many big-data applications, e.g. training deep neural networks as well as…

cs.CV2020

Unsupervised Video Representation Learning by Bidirectional Feature Prediction

Nadine Behrmann, Juergen Gall, Mehdi Noroozi

This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature pred…

cs.CV20202 cited

Adversarial and Natural Perturbations for General Robustness

Sadaf Gulshad, Jan Hendrik Metzen, Arnold Smeulders

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which…