Machine Learning
Build, train, and evaluate predictive models from first principles to deployment.
- 1Week 1
Foundations of Machine Learning
Do: Set up a Python notebook environment and load a public dataset (e.g. Titanic or Iris), exploring its shape and types.
Deliverable: A working notebook with the data loaded and summarised.
- 2Week 2
Data Preparation & Feature Engineering
Do: Clean the dataset: handle missing values, encode categorical fields, and scale numeric features.
Deliverable: A cleaned, model-ready feature set.
- 3Week 3
Supervised Learning
Do: Train a logistic regression and a decision tree on your data and compare them.
Deliverable: Two baseline models with accuracy scores.
- 4Week 4
Model Evaluation & Tuning
Do: Evaluate models with cross-validation and tune hyperparameters using grid search.
Deliverable: A tuning report comparing metrics.
- 5Week 5
Unsupervised Learning & Neural Networks
Do: Apply K-means clustering and build a small neural network on a sample dataset.
Deliverable: A clustering plot and a trained neural network.
- 6Week 6
Deployment & Capstone
Do: Package your best model behind a simple inference script or API and present it.
Deliverable: A deployable model and capstone presentation.
