Key Information
Tutor: Dr Andreas Joergensen
Course Level: Level 2
Course Credit: 1 credit
Prerequisites: Introduction to Machine Learning (or equivalent prior learning). Intermediate Python programming skills (numpy, matplotlib, functions, classes). Example code will be provided in each tutorial. No prior knowledge of PyTorch or Deep Learning is required.
Course Duration: 1-hour remote introduction (MS Teams) & 3 consecutive weekly 2-hour face to face teaching sessions.
Course Resources
Following on from the Introduction to Machine Learning course, this series of hands-on workshops will get you started with Deep Learning in Python, using the popular PyTorch library. In particular, the course will focus on so-called convolutional neural networks (CNN) for computer vision.
Syllabus:
- Neural network architectures
- Training and optimisation of neural networks
- Convolutional neural networks (CNN)
- Building and evaluating deep learning models in PyTorch
Learning Outcomes:
By the end of the course, you will be better able to:
- Explain the basic terminology and concepts of deep learning methods.
- Summarise applications of different neural network architectures, including CNN.
- Understand the implementation of neural networks in PyTorch, including their training and testing.
- Apply a range of neural network architectures in PyTorch, including CNN, to data.
- Assess the performance of a range of neural networks in PyTorch, including CNN.
Dates & Booking Information
There are no further sessions taking place this academic year. Course dates for 2025-26 will be available to book from late September.
To book your place, please follow the booking process advertised on the main programme page