Search Results for author: Bhairav Mehta

Found 8 papers, 3 papers with code

Region of Interest focused MRI to Synthetic CT Translation using Regression and Classification Multi-task Network

no code implementations30 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.

regression Value prediction

The Negative Pretraining Effect in Sequential Deep Learning and Three Ways to Fix It

no code implementations1 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.

Curriculum in Gradient-Based Meta-Reinforcement Learning

no code implementations19 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.

Benchmarking Meta-Learning +4

Generating Automatic Curricula via Self-Supervised Active Domain Randomization

1 code implementation18 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.

Reinforcement Learning (RL)

Active Domain Randomization

2 code implementations9 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.


A Scalable, Flexible Augmentation of the Student Education Process

no code implementations17 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.