Curriculum at a glance
A compact, hands-on path to understand AI concepts and build real projects.
Core modules
1. What is AI?
History, terminology, and where ML fits.
2. Python for ML
Essential libraries: numpy, pandas, matplotlib.
3. Machine Learning Basics
Supervised vs unsupervised, evaluation, train/test split.
4. Deep Learning
Neural nets, keras/pytorch intro, CNNs and RNNs.
5. Projects & Portfolio
Simple projects: image classifier, chatbot, recommendation demo.
6. Ethics & Safety
Bias, explainability, and responsible ML.
Quick exercises
Small tasks you can do in 15–60 minutes to practice.
- Load a CSV with pandas and inspect columns
- Train a simple linear regression on a sample dataset
- Build a tiny CNN on CIFAR-10 (or a subset)