Machine Learning Curriculum Index
A rigorous, undergraduate-to-industry engineering curriculum tailored for aspiring Machine Learning Engineers, Data Scientists, and AI Researchers.
Designed according to university academic standards and modern industry production requirements, this program bridges mathematical foundations
with hands-on data preprocessing, supervised/unsupervised algorithms, deep neural networks, natural language processing, and MLOps deployment pipelines.
- Master core mathematical prerequisites: Linear Algebra, Multivariate Calculus, Probability, and Statistics for machine learning.
- Build robust data preprocessing, exploratory data analysis (EDA), and feature engineering pipelines using NumPy, Pandas, and Scikit-Learn.
- Implement classical supervised learning algorithms: Linear Regression, Logistic Regression, Support Vector Machines, and Decision Trees from scratch.
- Explore advanced ensemble modeling techniques: Random Forests, Gradient Boosting (GBM), XGBoost, LightGBM, and CatBoost.
- Uncover hidden data patterns using unsupervised learning algorithms: K-Means Clustering, Hierarchical Clustering, PCA, and t-SNE.
- Design, train, and optimize deep neural networks (DNNs, CNNs, RNNs, and LSTMs) using PyTorch and TensorFlow / Keras.
- Process text and speech data using Natural Language Processing (NLP), Transformer architectures, BERT, and Large Language Models (LLMs).
- Deploy, monitor, and scale machine learning models into production using Docker, FastAPI, MLflow, and cloud endpoints (MLOps).
- Understand AI ethics, model bias, fairness metrics, explainable AI (SHAP/LIME), and responsible AI guidelines.
- Build an enterprise-grade end-to-end machine learning system as an engineering capstone project.