Prerequisites

Background material for getting the most out of the SUT-AI supplementary notebooks.

Overview

The supplementary notebooks are meant to be readable, practical, and useful as side material for artificial intelligence topics. You do not need to master everything below before opening a notebook, but these are the areas that make the material much easier to follow.

Mathematics

Artificial intelligence leans heavily on mathematical notation. A working comfort with calculus and linear algebra is enough for many notebooks, and a deeper review helps when the material moves toward optimization, probabilistic models, or deep learning.

Good review options:

Probability and Statistics

Many AI topics assume probability, random variables, estimation, expectation, conditioning, likelihoods, and uncertainty. You do not need to know every theorem by heart, but you should be able to follow probabilistic notation and basic statistical reasoning.

Good review options:

Data Structures and Algorithms

Some notebooks touch search, dynamic programming, graph structure, complexity, or implementation details. A standard undergraduate algorithms background is more than enough.

Good review options:

Python and Scientific Computing

The notebooks are written in Python. You should be comfortable reading Python, running notebooks, and understanding basic NumPy-style array operations.

Good review options:

Authors