I like deep neural nets.
I build models to understand how they actually work.
I explore vision and language problems.
Still building & still learning
I like deep neural nets.
I build models to understand how they actually work.
I explore vision and language problems.
Still building & still learning
End-to-end MLOps system for predicting EV battery State-of-Health (SoH) using NASA 18650 Li-ion dataset. Covers MLflow experiment tracking and model registry, FastAPI serving, Prometheus + Grafana …
Jupyter Notebook
Apache Spark pipeline that processes raw e-commerce events — views, cart adds, and sessions — through a Bronze→Silver→Gold medallion architecture to predict purchase intent. A Logistic Regression m…
Jupyter Notebook
PySpark ML pipeline for smart traffic congestion prediction with data generation, preprocessing, model training, evaluation, and streaming-style predictions.
Jupyter Notebook
ML-powered web app that predicts patient insurance charges using user inputs, deployed with Docker, CI/CD pipelines, Azure Container Registry, and Azure Web App.
Jupyter Notebook
A sandbox for exploring end-to-end machine learning operations: testing ideas, integrating tools, and building practical workflows around model development, deployment, and lifecycle management.
Jupyter Notebook
Classical OpenCV-based number plate detection with OCR
Jupyter Notebook