Data Science

Supervised & Unsupervised Learning

Model evaluation & performance metrics

Feature engineering & preprocessing

Ensemble methods (Boosting, Bagging)

Hyperparameter tuning

Handling imbalanced data

Neural networks (MLP, CNN, RNN, LSTM)

Transfer learning & pretrained models

Introduction to transformers

Big data fundamentals (Hadoop, Spark)

Data pipelines & real-time analytics

SQL & NoSQL databases

Model deployment with Flask / FastAPI

Docker & containerization

Monitoring & version control