# Prerequisites for Using the Maths, CS & AI Compendium: A Complete Guide > Master advanced AI, CS, and Maths topics with our compendium. No prior experience needed; learn everything from scratch with elementary math and basic Python. - Repository: [Henry Ndubuaku/maths-cs-ai-compendium](https://github.com/HenryNdubuaku/maths-cs-ai-compendium) - Tags: getting-started - Published: 2026-07-16 --- **You only need elementary mathematics and basic Python programming to start using the Maths, CS & AI Compendium, as all advanced topics including linear algebra and machine learning are taught from the ground up.** The HenryNdubuaku/maths-cs-ai-compendium repository is designed as a zero-to-hero educational resource that minimizes entry barriers. Whether you are a student transitioning into technical fields or a self-taught programmer exploring artificial intelligence, the prerequisites for using the Maths CS AI Compendium are intentionally minimal. According to the project's [`README.md`](https://github.com/HenryNdubuaku/maths-cs-ai-compendium/blob/main/README.md) (lines 49-50), the repository requires no external libraries, specialized hardware, or prior AI/ML experience to begin learning. ## Minimum Requirements to Get Started The compendium explicitly defines two core competencies needed before diving into the material. These foundational skills provide the necessary scaffolding for all subsequent chapters, from basic vector spaces to advanced GPU programming. ### Elementary Mathematics Foundation You must possess familiarity with high-school-level algebra, geometry, and basic calculus concepts. This includes understanding variables, functions, coordinate systems, and limits. The text assumes no prior exposure to university-level mathematics, making it accessible to high school graduates and career-switchers alike. ### Basic Python Programming Skills The ability to write and execute simple Python scripts is essential. Specifically, you should understand control flow (loops and conditionals), function definitions, and standard library usage. The code style throughout the repository mirrors this beginner-friendly approach, avoiding complex abstractions until they are properly introduced. ## Verifying Your Python Foundation Before proceeding to advanced chapters, ensure you can execute and understand scripts similar to those found in early sections. The following examples demonstrate the exact level of Python proficiency expected across the compendium. Calculate basic probabilities using arithmetic operations: ```python # Example 1: Computing a simple probability # Prerequisite: basic arithmetic and Python functions def probability_of_head(num_trials, heads): """Return the empirical probability of getting `heads` heads in `num_trials` flips.""" return heads / num_trials print(probability_of_head(10, 7)) # → 0.7 ``` Visualize data using standard visualization libraries: ```python # Example 2: Visualising a vector in 2‑D # Prerequisite: knowledge of lists and the `matplotlib` library (commonly pre‑installed) import matplotlib.pyplot as plt vector = [3, 4] # elementary vector concept plt.quiver(0, 0, vector[0], vector[1], angles='xy', scale_units='xy', scale=1) plt.xlim(0, 5); plt.ylim(0, 5) plt.title("2‑D Vector") plt.grid(True) plt.show() ``` These snippets reflect the practical coding standards maintained throughout the repository, from `chapter 01: vectors/01. vector spaces.md` through advanced machine learning sections. ## What You Do Not Need The compendium explicitly removes common barriers to entry in AI education. According to the source code analysis, no external libraries beyond standard Python are required to begin reading, and specialized hardware such as GPUs is optional rather than mandatory. Topics including linear algebra, probability theory, machine learning fundamentals, and GPU programming are introduced incrementally within their respective chapters. ## Key Entry Points in the Repository Understanding the file structure helps verify your readiness against actual content: - **[`README.md`](https://github.com/HenryNdubuaku/maths-cs-ai-compendium/blob/main/README.md)**: Contains the authoritative list of prerequisites and high-level curriculum overview. - **`chapter 01: vectors/01. vector spaces.md`**: The first technical chapter assumes only elementary mathematics and basic Python literacy, serving as the true starting point for testing your background. - **`chapter 06: machine learning/01. classical machine learning.md`**: Demonstrates how advanced topics build upon earlier foundations, requiring no prior ML knowledge. - **[`mcp/src/index.ts`](https://github.com/HenryNdubuaku/maths-cs-ai-compendium/blob/main/mcp/src/index.ts)**: An optional Model Context Protocol server implementation for advanced users; this file is not required for reading the educational material but provides a usage example for those exploring tool integration. ## Summary - **Elementary mathematics** (high-school algebra, geometry, and basic calculus) provides the quantitative foundation. - **Basic Python programming** (loops, functions, and standard libraries) enables execution of all examples. - **No prior AI/ML experience** is necessary, as the compendium teaches advanced topics from first principles. - **No specialized hardware** or external library dependencies are required to begin learning. ## Frequently Asked Questions ### Do I need prior machine learning experience to use this compendium? No prior machine learning or artificial intelligence experience is required. The repository is structured to introduce ML fundamentals, including classical algorithms and modern architectures, from the ground up in `chapter 06: machine learning/01. classical machine learning.md`. ### Is specialized hardware like GPUs required? Specialized hardware is not required to start. While later chapters cover GPU programming and advanced AI architectures, the initial material and foundational concepts run entirely on standard CPU-based Python environments. ### What if I only know basic Python but struggle with math? The compendium is designed to teach mathematical concepts alongside code. As long as you have high-school-level algebra and basic calculus familiarity, the text develops linear algebra and probability theory incrementally, pairing mathematical explanations with executable Python examples. ### Are there any mandatory external libraries to install? No mandatory external libraries are required to begin reading the material. While some examples utilize `matplotlib` for visualization (commonly pre-installed in most Python distributions), the core educational content relies only on standard Python capabilities. Optional components like the MCP server in [`mcp/src/index.ts`](https://github.com/HenryNdubuaku/maths-cs-ai-compendium/blob/main/mcp/src/index.ts) exist for advanced integrations but are not prerequisites for learning.