Het Shah
Hello! કેમ છો? I am Het Shah, a Computer Science Undergraduate from Birla Institute of Technology and Science Pilani, K. K. Birla Goa Campus. I am currently working as a Research Fellow at the PROSE team at Microsoft Research where I am currently developing a new skill for migrating code from older .NET versions to newer .NET version. The work is done in collaboration with the Copilot X team and Migration team at Microsoft Research. Prior to joining as a RF I spent a year as a Research Intern at Microsoft Research India where I was advised by Dr. Navin Goyal. Previously, I completed my undergraduate thesis at Visual Computing Lab(VCL) at IISc Bangalore, where I was advised by Prof. Anirban Chakraborty and Gaurav Kumar Nayak on “Incremental Learning for Animal Pose Estimation”.
I was an Undergraduate Student Researcher at Anuradha and Prashanth Palakurthi Centre for Artificial Intelligence Research (APPCAIR) Lab at my University where I worked on “Iterative Knowledge Distillation” and “Reasoning abilities of Transformer networks”. I have also taught various courses related to Python and Deep Learning (you can find the list here).
My current research interests are
- how humans brain can motivate neural network models specifically how humans reason and how can we create models to solve reasoning tasks with Neural Networks;
- how to effectively represent data (nerually or neuro-symbolically) to help us in inducing reasoning in the models
News
Jul 4, 2022 | I will be joining the PROSE team at Microsoft Research as a Research Fellow! |
May 6, 2021 | I will be joining Microsoft Research India as a Research Intern where I will be advised by Navin Goyal! |
Apr 30, 2021 | Our team (Avishree Khare and I) have been selected for ESOWC 2021 to work on the ML4Land project! |
Dec 3, 2020 | I’ll be joining VCL Lab at IISc Bangalore, India as research intern for the next semester, where I’ll be pursuing my undergraduate thesis. I’ll be looking at transfer of pose estimation networks from humans to animals. |
Jul 11, 2020 | My first paper “An Autoencoder Based Approach to Simulate Sports Games” is accepted at the 7th Workshop on Machine Learning and Data Mining for Sports Analytics at ECML-PKDD 2020. |