Module 4: Machine Learning & Deep Learning Foundations#

CodeVision Python Training

Contents#

  • Group 1: The Big Picture (Sections 4.1-4.5)

  • Group 2: Anatomy of a Neural Network (Sections 4.6-4.10)

  • Group 3: How Models Learn (Sections 4.11-4.15)

  • Group 4: Reality, Frameworks, and Why This Matters (Sections 4.16-4.20)


Welcome to Module 4#

This module explains how machine learning and deep learning actually work, and why modern AI systems (including LLMs) behave the way they do.

It is conceptual first, with light, real code to ground ideas. By the end of this module, the behaviour of LLMs should feel inevitable, not mysterious.

This module builds directly on:

  • Module 1: Python fundamentals (functions, JSON, notebooks)

  • Module 2: Data work with Pandas and visualisation

  • Module 3: LLM Fundamentals (inference, hallucinations, constraints)


What You Will Learn#

Topic

Why It Matters

AI vs ML vs DL vs GenAI

Set correct expectations and vocabulary

Neural network anatomy

Understand what models actually are

Weights, biases, activations

Grasp the building blocks

Loss functions & gradient descent

Know how models learn

Overfitting vs underfitting

Recognise and mitigate common failures

PyTorch vs TensorFlow/Keras

Understand the two dominant frameworks

Why LLMs hallucinate

Connect training dynamics to behaviour

Why grounding (RAG) is required

Bridge to enterprise reliability


Prerequisites#

Before starting this module, ensure you have:

  • Completed Module 1 (Python Foundations)

  • Completed Module 2 (Python for Data Work)

  • Completed Module 3 (LLM Fundamentals)


Module 4 Learning Path#

  1. Content - Work through the interactive notebook

  2. Quiz - Test your understanding (auto-graded)

  3. Assessment - Written explanations demonstrating comprehension (auto-graded)

  4. Resources - Additional learning materials


End of Module 4 Introduction#

Click Content in the navigation to begin the interactive lesson.