Sourin Dey

Columbia, South Carolina · (307) 761-3781 · sourin@email.sc.edu

I am doing PhD in Computer Science at the University of South Carolina with Deep Learning and Data Science specialization

Internship Experience

Core R&D PhD intern at Dow Chemicals (Summer 2024)


I have worked with the core R&D team's Data Science group to develop generative models to discover novel products. This involved working on auto encoders, knowledge graph, high performance computing.

Research Interests

Optimization Techniques

Deep Learning & Neural Networks

Reinforcement Learning

Computer Vision

Human Robot Interaction

Education

University of South Carolina

Doctorate - Computer Science
Selected Courses: Data Mining & Warehousing, Computer Processing of Natural Language, Neuromorphic Computing
August 2021 - Present

University of Wyoming

Master - Computer Science
Selected Courses: Intro to AI, Deep Reinforcement Learning & Control, Randomness in Computation
August 2019 - July 2021

Khulna University of Engineering & Technology

Bachelor of Science - Electrical and Electronic Engineering
Selected Courses: Digital Image Processing, Digital Signal Processing
April 2014 - May 2018

Research Experience

PhD Research

Graduate Research Assistant
  • I developed an Atomistic Line Graph Neural Network based model to learn electronic structure of crystals for predicting eigenvalue, a critically important opto-electric property. This model significantly outpaces the conventional DFT method, which is known for its high computational costs
  • I am currently working to develop a graph neural network based contrastive-learning model that will help to find similar crystal structures from all available structures in material projects. I used Crystal Graph Convolution for message passing generates the embedding for contrastive model. This project will greatly narrow down search space for material/drug discovery on specific application.
    • August 2021 - Present

    Research Experience

    MS Research

    Graduate Research Assistant

    I worked on a project to optimize the Laser-Induced Graphene Process(LIG) using AI. LIG enables the production of high-quality graphene which has enhanced next-generation nano-circuit design. I investigated the exploration-exploitation trade-off effect in optimizing the LIG. Besides the investigation, I worked at the AIM Center to draw conductive lines of graphene powered by AI.

    Automated Material Processing: I have implemented a fully automated Laser-Induced Graphene process. This has led to no human in the loop and accelerated the manufacturing process.

    August 2019 - July 2021

    Undergraduate Thesis

    Formant-based Perceptual Space Classification is focused on detecting the Bengali vowel from continuous speech. High Accuracy by SVM RBF Kernel Classifier is gained. This will enhance the emotional state recognition research in the Bengali language.

    June 2017 - May 2018

    Skills

    Programming Languages & Tools
    • C
    • C++
    • High Performance Computing
    • Shell Scripting
    • Python (Scikit-Learn, PyTorch, Keras, PyGame, PyGAM, Tensorflow), R
    • R(mlrMBO,mlr,caret)
    • C++, C, Android Studio with Java Programming
    • Linux, Windows, Android
    • Git
    • Microsoft Office, LaTex

    Publications

    • Optimizing Laser-Induced Graphene Production

      Prestigious Applications of Intelligent Systems, PAIS 2022, Vienna, Austria
      Authors: Lars Kotthoff, Sourin Dey, Vivek Jain, Alexander Tyrrell, Hud Wahab, Patrick Johnson

    • Scalable deeper graph neural networks for high-performance materials property prediction

      Patterns 2022
      Authors: SS Omee, SY Louis, N Fu, L Wei, S Dey, R Dong, Q Li, Jianjun Hu.

    Extracurriculars

    I have interests in wildlife photography. During my master's days, I explored rural Wyoming and countrysides of the colorful Colorado. Have a look of my stills of the places Wyoming Days!!