Ashrya Agrawal

Ashrya Agrawal

Computer Science Junior

BITS Pilani - Pilani Campus

About me

Ashrya Agrawal is an undergraduate Computer Science student at BITS Pilani, Pilani Campus. His Research Interests are wide-ranged subtopics in Deep Learning and Machine Learning. Within Deep Learning, he has interest and experience in Computer Vision, Natural Language Processing, and Reinforcement Learning. He is also interested in Fairness in Machine Learning to mitigate racial bias, gender bias, etc.

He works as an undergraduate Research Assistant at Advanced Data Analytics and Parallel Technologies Lab, BITS Pilani. Here, he works on Video Description generation.

During summer and fall of 2020, he worked on tackling practical issues being faced by the industry in mitigating bias in decision support tools. The work led to a research paper and Julia’s first bias audit and mitigation toolkit which solves many practical challenges faced by researchers and practitioners in bias mitigation with existing toolkits.

Interests

  • Computer Vision
  • Natural Language Processing
  • Reinforcement Learning
  • Fairness in Machine Learning

Education

  • B.E. (Hons.) Computer Science, 2022

    BITS Pilani - Pilani Campus

Experience

 
 
 
 
 

ML Intern

Wipro Ltd.

May 2020 – Jun 2020 Bangalore

Worked on NLP of Chatbot to be used by 170k Wipro employees for automatic query answering

Responsibilities include:

  • Deep Learning Solution
  • Data Preprocessing and Model building
  • Deploying
 
 
 
 
 

JSOC Intern

JuliaComputing

May 2020 – Oct 2020 Remote
  • Developed Fairness.jl, a comprehensive toolkit in Julia for bias audit and mitigation
  • Benchmarked fairness algorithms and demonstrated practical considerations like generalization error which further lead to a publication
 
 
 
 
 

Research Assistant

Advanced Data Analytics and Parallel Technologies Lab, BITS Pilani

Jan 2020 – Present Pilani
  • Working to improve SOTA for Video Description generation under Prof. Navneet and Prof. Poonam
  • Explored use of first Visio-Textual Knowledge Base in Video Description generation
 
 
 
 
 

Teaching Assistant

Computer Science Department BITS Pilani

Aug 2019 – Nov 2019 Pilani
Taught Computer Programming course to a group of 100 students through Theory and Lab Sessions.

Accomplish­ments

IBM HackChallenge National Winner

Created Friend Affinity Finder which uses social media data to perform NLP analysis.

  • Using social media data, it gives insights about a friend’s Big 5 personality traits, general tone and interests.
  • This information is then used by clustering module to compute friendship affinity and subsequently categorize friends.
See certificate

JEE Mains

Secured 99.94 percentile (All India Rank 576) while competing with 1 million students.

KVPY Fellow SA & SX

Recipient of the prestigious KVPY fellowship twice.

  • All India Rank 185 while competing with about 60,000 other students in grade 12.
  • All India Rank 685 while competing with 50,000 other students, in grade 11.

Top 1% : National Standard Examination in Physics

Top 1% in the qualifying examination for International Physics Olympiad.
See certificate

Top 1% : National Standard Examination in Chemistry

Qualified to next stage for Indian National Chemistry Olympiad while securing top 1% marks in the qualifying exam for International Chemistry Olympiad.
See certificate

Talks

ACM Hour of Code

ACM Hour of Code

Python SIG Lecture

Python SIG Lecture

Publications

Debiasing classifiers: is reality at variance with expectation?

Many methods for debiasing classifiers have been proposed, but their effectiveness in practice remains unclear. We evaluate the …
Debiasing classifiers: is reality at variance with expectation?

Skills

Python

Pytorch

Tensorflow

Julia

Backend Development

Data Science

Contact