Machine Learning Engineering: From Models to Production
A complete learning path covering supervised learning, model evaluation, deep learning basics and deploying machine learning models to production.
About this learning path
This learning path takes you from your first scikit-learn model to deploying a machine learning service that other applications can use. It combines theory — just enough math to understand what algorithms are doing — with plenty of hands-on coding.
You will build regression and classification models, tune them with cross-validation, learn the basics of neural networks with PyTorch and package your work with modern MLOps practices such as experiment tracking, containerisation and monitoring.
What you'll learn
- Prepare features and split data correctly to avoid leakage
- Train and compare regression, classification and clustering models
- Evaluate models with the right metrics and cross-validation
- Build and train simple neural networks with PyTorch
- Track experiments and version models
- Deploy a model as a REST API and monitor it in production
Syllabus
6 modules · 12 weeks · approx. 84 hours total
Module 1ML foundations
- The machine learning workflow
- Feature engineering
- Train/validation/test splits and data leakage
Module 2Supervised learning
- Linear and logistic regression
- Decision trees, random forests and gradient boosting
- Handling imbalanced data
Module 3Model evaluation
- Accuracy, precision, recall and F1
- ROC curves and AUC
- Hyperparameter tuning
Module 4Unsupervised learning
- k-means and hierarchical clustering
- Dimensionality reduction with PCA
- Anomaly detection
Module 5Deep learning basics
- Neural networks with PyTorch
- Training loops and optimisers
- Transfer learning
Module 6MLOps and deployment
- Experiment tracking
- Serving a model with FastAPI and Docker
- Monitoring drift in production
Requirements & who it's for
Prerequisites
- Working knowledge of Python
- Basic pandas skills (see Data Analysis with Python)
- High-school level algebra
Who this is for
- Data analysts moving into machine learning
- Software engineers adding ML skills
- Computer science students
Frequently asked questions
How much math do I need?
You need comfort with basic algebra. Key ideas from statistics and linear algebra are explained intuitively as they come up.
What will I build?
Several end-to-end projects, finishing with a deployed prediction API you can add to your portfolio.
Read before you start
What Is Machine Learning? A Plain-English Guide for Beginners
Machine learning explained without jargon: how computers learn from data, the main types of ML, real examples and how to get started.
SQL for Beginners: The Essential Commands Every Data Analyst Needs
A hands-on SQL tutorial covering the handful of commands that answer most real-world data questions — with copy-ready examples.
Data Analyst vs Data Scientist: Differences, Skills and Which to Choose
What each role actually does day to day, the skills and tools you need, and a simple checklist to help you choose the right data career.
You may also like
CourseFreeData Analysis with Python, Pandas and Visualization
CourseFreeAI Fundamentals: Concepts, Tools and Real-World Applications
CourseFreePrompt Engineering & Generative AI for Professionals
CourseFree