Complete ML engineering curriculum: math foundations through deep learning and production deployment. Build 5 real projects along the way.
Week 1 · Days 1-45
The Bedrock: Math & Python
Days 1-45
- Python for data science (NumPy, Pandas, Matplotlib)
- Linear algebra: vectors, matrices, eigendecomposition
- Calculus: gradients, chain rule, optimization
- Probability & statistics: distributions, Bayes, hypothesis testing
- Data preprocessing and feature scaling
Project
Exploratory data analysis pipeline
NumPy
Pandas
Linear Algebra
Calculus
Statistics
Week 7 · Days 46-90
Predict & Classify: Supervised Learning
Days 46-90
- Linear & logistic regression from scratch
- Decision trees and random forests
- Support vector machines (theory + scikit-learn)
- K-Nearest Neighbors and distance metrics
- Ensemble methods: bagging, boosting, stacking
- Cross-validation and hyperparameter tuning
Project
The Oracle: Real estate price prediction
scikit-learn
Regression
Classification
Ensembles
Week 13 · Days 91-135
Patterns & Rewards: Unsupervised & RL
Days 91-135
- Clustering: K-Means, DBSCAN, hierarchical
- Dimensionality reduction: PCA, t-SNE, UMAP
- Anomaly detection: Isolation Forest, autoencoders
- Recommendation systems: collaborative + content-based
- RL fundamentals: MDPs, Q-learning, policy gradients
Project
The Matchmaker: Movie recommendation engine
Clustering
PCA
Anomaly Detection
RL Basics
Week 20 · Days 136-180
Deep Intelligence: Neural Networks
Days 136-180
- Neural networks from scratch (forward/backprop)
- CNNs for image classification and object detection
- RNNs, LSTMs, and sequence modeling
- Transformers and attention mechanisms
- Transfer learning and fine-tuning
- NLP: tokenization, embeddings, sentiment analysis
- Model deployment: Docker, FastAPI, cloud serving
Project
Visionary (image classifier) + Sentient (NLP analyzer)
PyTorch
CNNs
Transformers
NLP
MLOps