Introduction to Neural networks in PyTorch (In-person)

Audience Level: Intermediate

This course is aimed at intermediate Python programmers who want an introduction to the underlying theory of neural networks and how to apply deep learning to data classification problems. This training session is ideal for participants who have a foundational understanding and are looking to expand their skills. More detailed prerequisites are provided below.

Session Information:

This course is aimed at intermediate Python programmers who want an introduction to the underlying theory of neural networks and how to apply deep learning to data classification problems.

The course materials will be made available soon.

Prerequisites:

You should be comfortable programming in Python. Experience with the content of our Applied Data Analysis in Python course (https://bristol-training.github.io/applied-data-analysis-in-python/) or equivalent is strongly recommended.

You should already be comfortable with:

• Running python in a Jupyter notebook

• Working with dataframes/numpy arrays

• Plotting with matplotlib/seaborn

• Defining functions

• Using classes such as sklearn models

• Test train split and validating models

The theory of deep learning includes ideas from calculus and linear algebra. Understanding the idea of a derivative of a function would be strongly recommended. Having some notion of matrix multiplication would be useful but is not essential.

Action required before the session:

Please bring along your own laptop with a working Python installation, including numpy, pandas, sklearn and PyTorch (ready to run locally). For more information on installing PyTorch, we recommend you look at their documentation website: https://pytorch.org/get-started/locally/
If you’re unsure of which option to pick, we recommend you choose the “CPU” option.

We are running an in-person and online JGI drop-in installation session on Friday 30th May from 11:30-12:45 - if you require any help in installing any software please attend this session.

Intended learning outcomes

By the end of this course, you will:

• Understand the basic theory of a feed forward multi layer perceptron.

• Start to get the grips with PyTorch, tensors and writing classes in Python.

• Understand how to pre-process data for training (including test train split)

• Understand how to feed forward data and evaluate test loss for a neural network.

• Have a basic intuition for what gradient descent and back propagation are.

• Implement back propagation to update our weights and biases and reduce our test loss.

What this course will not cover

Deep learning and neural networks are a huge field of active research that we cannot cover in 3 hours. This class is designed to cover the learning outcomes above and serve as a prerequisite to further topics in AI, neural networks, and deep learning, such as:

• Cross entropy loss and more advanced optimisers

• Training neural networks using High Powered Computing (HPC) resources

• Convolutional Neural Networks (CNNs) for image/video analysis

• Recurrent Neural Networks (RNNs) for time series and natural language processing

• Transformers and Large Language Models (LLMs)

• Graphical Neural Networks (GNNs)

Code of Conduct

Please look at our Code of Conduct for all online and in-person events organised by the JGI.

Bristol Data Week 2025

This event is part of Bristol Data Week 2025, organised by the Jean Golding Institute taking place from Monday 2nd June - Friday 6th June. Bristol Data Week is a leading platform for learning, discussion, and collaboration in data science and AI. It brings together researchers, industry experts, policymakers, and community groups to explore the latest advancements in data and technology, addressing real-world challenges and shaping the future of responsible AI.

This year, we will be running a week long series of events featuring:

• Expert-led workshops and training on cutting-edge data science and AI topics.
• Thought-provoking panel discussions with leading voices in the field.
• Opportunities to network with researchers, industry professionals, and policymakers.

Keep up to date with activities happening throughout Bristol Data Week on the Jean Golding Institute website, follow us on Bluesky, LinkedIn and tag us with #BristolDataWeek2025 or #BDW2025.

Please be aware that photography and recording of the sessions may be taking place. Please let us know if you would not like to be filmed by contacting jgi-admin@bristol.ac.uk