Introduction
Welcome to Getting Started with AI (part 2) — a practical, hands-on continuation of our introductory AI course. In this session we move beyond the core ideas covered in part 1 and focus on applying machine-learning and AI techniques. We will work through several widely used methods — from exploratory data analysis (EDA) to random forests and neural networks — and conclude by showing how modern LLMs can be integrated into applications and analysis pipelines.
No prior programming experience is required. By the end of the session, you will have gained hands-on intuition for how these tools behave in practice and the practical steps involved in building and using AI systems.
Learning Objectives
By the end of this course, you will be able to:
- Perform basic exploratory data analysis (EDA) to understand and prepare a dataset
- Train and interpret classical machine‑learning models such as random forests
- Build and evaluate simple neural networks
- Understand practical considerations in model training, evaluation, and workflow design
- Use large language models via an API and integrate them into simple applications or analysis tasks
About this Course
Each part combines short explanations with interactive visualisations and hands-on examples so you can immediately see the concepts in action. Parts 2 and 3 include guided coding exercises; no setup is required beyond a web browser. The materials are self-contained and designed to be revisited at your own pace after the session.
These course materials have been designed and developed by the Jean Golding Institute, University of Bristol: Pau Erola (lead), Rita Rasteiro, Josh Tyler, Ben Westhenry, Richard Lane, James Thomas.
We used AI assistance in line with institutional guidance:
- Microsoft Copilot (GPT-5) – Writing assistance
- Claude (Sonnet 4) – Writing assistance and example code generation
- Google Gemini (Gemini 3) – Image generation
For queries related to this course please contact jgi-training@bristol.ac.uk.