no code implementations • 30 Mar 2022 • Sandeep Kaushik, Mikael Bylund, Cristina Cozzini, Dattesh Shanbhag, Steven F Petit, Jonathan J Wyatt, Marion I Menzel, Carolin Pirkl, Bhairav Mehta, Vikas Chauhan, Kesavadas Chandrasekharan, Joakim Jonsson, Tufve Nyholm, Florian Wiesinger, Bjoern Menze
In this work, we present a method for synthetic CT (sCT) generation from zero-echo-time (ZTE) MRI aimed at structural and quantitative accuracies of the image, with a particular focus on the accurate bone density value prediction.
no code implementations • 1 Jan 2021 • Julian G. Zilly, Franziska Eckert, Bhairav Mehta, Andrea Censi, Emilio Frazzoli
Negative pretraining is a prominent sequential learning effect of neural networks where a pretrained model obtains a worse generalization performance than a model that is trained from scratch when either are trained on a target task.
1 code implementation • 17 Nov 2020 • Bhairav Mehta, Ankur Handa, Dieter Fox, Fabio Ramos
Simulators are a critical component of modern robotics research.
no code implementations • 9 Sep 2020 • Jacopo Tani, Andrea F. Daniele, Gianmarco Bernasconi, Amaury Camus, Aleksandar Petrov, Anthony Courchesne, Bhairav Mehta, Rohit Suri, Tomasz Zaluska, Matthew R. Walter, Emilio Frazzoli, Liam Paull, Andrea Censi
As robotics matures and increases in complexity, it is more necessary than ever that robot autonomy research be reproducible.
no code implementations • 19 Feb 2020 • Bhairav Mehta, Tristan Deleu, Sharath Chandra Raparthy, Chris J. Pal, Liam Paull
However, specifically in the case of meta-reinforcement learning (meta-RL), we can show that gradient-based meta-learners are sensitive to task distributions.
1 code implementation • 18 Feb 2020 • Sharath Chandra Raparthy, Bhairav Mehta, Florian Golemo, Liam Paull
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal.
2 code implementations • 9 Apr 2019 • Bhairav Mehta, Manfred Diaz, Florian Golemo, Christopher J. Pal, Liam Paull
Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters.
no code implementations • 17 Oct 2018 • Bhairav Mehta, Adithya Ramanathan
We present a novel intelligent tutoring system which builds upon well-established hypotheses in educational psychology and incorporates them inside of a scalable software architecture.