Introduction to Artificial Intelligence with Python

What you'll learn

• Set up a reproducible Python AI environment and tooling (Jupyter, virtual environments, package managers)
• Refresh and apply Python essentials for data science using NumPy, Pandas, and visualization libraries
• Frame AI problems and choose appropriate modeling approaches for real-world tasks
• Use linear algebra, calculus, probability, and statistics to understand model behavior
• Clean data, perform exploratory analysis, and engineer effective features
• Train, tune, and validate supervised and unsupervised models with rigorous evaluation
• Build, train, and debug neural networks using PyTorch
• Understand key deep learning architectures (CNNs, RNNs/Transformers) and apply them to CV and NLP
• Deploy models, implement basic MLOps workflows, and monitor model performance in production
• Apply responsible AI practices including fairness, interpretability, and robustness

Prerequisites

Basic Python programming and comfort with algebra; no advanced math or ML experience required, but willingness to learn foundational math is expected.

Skills you'll gain

• Python for AI
• Data wrangling and EDA
• Feature engineering
• Statistical inference and probability
• Linear algebra for ML
• Supervised and unsupervised learning
• Model evaluation and validation
• Optimization and regularization
• Neural networks with PyTorch
• Model deployment and MLOps
• Responsible AI practices