Machine Learning Fundamentals for Practitioners
- Hands-on AI and data science techniques from working practitioners
- Structured program with clear milestones and real-world datasets
- Accessible remotely — join from anywhere in Ukraine
About this program
The gap between theory and practice
Most introductory ML courses spend weeks on math derivations before touching real data. This program starts with working code on week one and introduces theory when it explains something you have already seen break.
You will train models on structured datasets, measure their actual performance, and learn why a model that looks accurate on paper can fail completely in production.
Core topics
- Supervised learning: linear and logistic regression, decision trees, random forests, gradient boosting
- Unsupervised learning: k-means clustering, PCA for dimensionality reduction
- Model evaluation: cross-validation, precision/recall tradeoffs, ROC curves
- Pipelines: feature engineering, preprocessing with scikit-learn, saving and loading models
Prerequisites
Participants should be comfortable writing Python functions and working with pandas DataFrames. A refresher on basic statistics is provided in week one.
Workload
Expect seven to eight hours per week, including two live sessions and independent assignments. Recorded sessions are available for one year after enrollment.
Program structure
-
Week 1–2 — Data Preparation and Baselines
Feature types, encoding, scaling, and building a first baseline model.
-
Week 3–4 — Supervised Learning Models
Tree-based methods, ensemble techniques, hyperparameter tuning with GridSearchCV.
-
Week 5 — Evaluation and Diagnostics
Confusion matrices, learning curves, bias-variance analysis.
-
Week 6 — Unsupervised Methods
Clustering use cases, PCA for feature reduction, anomaly detection basics.
-
Week 7–8 — Deployment Basics
Saving models with joblib, building a simple REST API with Flask, monitoring drift.
-
Week 9 — Capstone Project
End-to-end ML pipeline on a provided business dataset with written report.