Data Science & AI/ML
Build and deploy real machine learning models, from data to production.
Overview
This advanced track is built for people who want to go beyond analysis and build predictive systems. You will cover the full machine learning lifecycle — from data preparation and model building to evaluation and deployment — grounded in real-world case studies.
Expect to write a lot of code, break a lot of models, and come out the other side able to design ML solutions to real business problems.
What you'll learn
- Build and evaluate supervised and unsupervised ML models
- Train neural networks using TensorFlow or PyTorch
- Prepare and engineer features from real-world datasets
- Deploy a trained model as a working API
- Apply ML techniques to computer vision or NLP problems
Curriculum
5 modules • 15 lessons • 16 weeks
Module 1: Python & Math for ML
The technical foundation every ML engineer needs.
- Python for data science
- Linear algebra & probability essentials
- NumPy & Pandas at scale
Module 2: Machine Learning Fundamentals
Core algorithms behind most real-world ML systems.
- Supervised vs unsupervised learning
- Regression & classification
- Model evaluation & validation
Module 3: Deep Learning
Build neural networks for complex problems.
- Neural network fundamentals
- Introduction to TensorFlow / PyTorch
- Computer vision & NLP basics
Module 4: MLOps & Deployment
Take a model from notebook to production.
- Model packaging
- Deploying models as APIs
- Monitoring model performance
Module 5: Capstone Project
Design, build, and deploy an original ML solution.
- Problem selection
- End-to-end model build
- Deployment & presentation
Projects & Case Studies
This course's project gallery is still in development — check back soon.
Requirements
- Basic programming experience (any language)
- Comfort with high-school level math is helpful, not required
- A laptop capable of running Python (Windows, macOS, or Linux)
Frequently asked questions
Is this course suitable for absolute beginners?
This is an advanced track. Basic programming experience is recommended — if you are new to coding, start with Data Analytics first.
Will I need a powerful computer or GPU?
No — coursework runs on cloud notebooks, so a standard laptop is enough for every project.
What can I do with this after graduating?
Graduates are prepared for roles like Machine Learning Engineer, Data Scientist, and AI Developer.
