About Me

  • What I am?Sweet but Psycho
  • Where I am?Ireland
  • How I am?Okaaayish
  • Who I am?a student?
  • Why I am?Won that same race like yourself

Hello!

I am Urja (pronounced oorja) and have recently finished my PhD at Munster Technological University, Ireland. My PhD was in Explainable AI and I loved exploring, studying, and optimising the mechanistic interpretability of the models!

Besides this, I think I am an average human being living life. I get so much fun from dancing and cooking (becoming good at cocktails as well!). I love to be good at what I do and try to help others in becoming aware and appreciative of technological advancements.

Professionally..

  • Education

  • PhD

    Munster Technological University, Ireland (2019-2024)

  • B.Tech

    National Institute of Technology, Raipur, India (2014-2018)

  • Publications

  • Optimal Neighborhood Contexts in Explainable AI: An Explanandum-Based Evaluation

    IEEE Open Journal of the Computer Society (2024)

  • On the Impact of Neighbourhood Sampling to Satisfy Sufficiency and Necessity Criteria in Explainable AI

    Causal Learning and Reasoning, UCLA, 2024

  • Explaining Medical Workflows via Feature Importance and Performance Metrics

    IEEE Computer Based Medical Systems, 2021

  • Work Experience

  • Software Engineer

    Optum Global Solutions - 1Y, 3mos (2018-19)

Skills

Mechanistic InterpretabilityStrong
Machine/Deep LearningStrong
Software EngineeringStrong
Presentation & CommunicationStrong

Research70%

Analytics60%

Statistics75%

Deep learning frameworks40%

System Design70%

Machine Learning70%

Technical writing85%

Backend Development70%

Medium Blog

Feb. 04th 2022

Counterfactuals and their Evaluation

Counterfactuals and some evaluation metrics from the literature for assessing how good or bad a counterfactual explanation is.

Aug. 24th 2021

Bayesian Statistics and Causal Inference

In this post, I have shared the relationship shared between the domain of Bayesian Statistics and Causal Inference.

Aug. 17th 2021

LLMs and Interpretability

This article will explain the current landscape of research aimed at identifying and addressing these issues of false and inaccurate information.