Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View yuvipaloozie's full-sized avatar
1 follower · 3 following

Block or report yuvipaloozie

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yuvipaloozie/README.md

Hi, I'm Yuvraj!

I currently work as a Process Automation Engineer, passionate about intersection of complex manufacturing processes and the data they produce. My goal is to specialize in the intersection between physical sciences and machine learning, specifically in computer vision and predictive modeling.

🎓 Education

  • M.S. Data Science (2027) | Georgia Institute of Technology
  • B.S. Chemical Engineering (2024) | Georgia Institute of Technology

🔭 Ongoing Projects and Research

  • Osteoclast Segmentation: (In cooperation with Sarah Szabo and PCOM GA) Developing a TransU-Net architecture with semi-supervised learning to segment and count osteoclasts from microscope imagery to assist in medical research.
  • Reinforcement Learning for Process Control: Creating and testing effectiveness of RL agents on chemical processes in varying complexity for process control.

✍️ Writing

  • Mechanistic Interpretability: Working on a blog series comparing CNN architectures to the human visual system.
  • ML vs DL: Working on projects/corresponding pieces demonstrating how carefully engineered ML models can outperform standard DL models.

Tech Stack

Python MATLAB SQL TypeScript

Pinned Loading

  1. Arrythmia-Classification-with-ML Arrythmia-Classification-with-ML Public

    Utilizing poincare analysis and statistical moments to create a ML model that rivals DL model performance on a complex ECG dataset

    Jupyter Notebook

  2. CHANA CHANA Public

    Utilizing a TransUNet CNN architecture to automate the counting of multinucleated osteoclasts with the data augmentation and semi-supervised learning

    Jupyter Notebook

  3. Predicting-Chemistry-with-GNNs Predicting-Chemistry-with-GNNs Public

    Utilizing various graph neural networks GNN to improve prediction accuracy on HOMO-LUMO gap and 3D coordinates for over 138000 simulated molecules

    Jupyter Notebook

  4. Data-Driven-Swing-Trading Data-Driven-Swing-Trading Public

    Implementing various quantitative/ML-driven models to create a profitable swing trading strategy

    Jupyter Notebook

  5. Semiconductor-Yield-Optimization-and-RCA Semiconductor-Yield-Optimization-and-RCA Public

    Utilizing machine learning on real-world semiconductor manufacturing data to predict batch success rate probability based on sensor readings

    Jupyter Notebook