COMP0197: Applied Deep Learning

UCL Module | CS | UCL Moodle Page

Term 2, Academic Year 2025-26

1. Development environment

The module tutorials (see bellow) and coursework use Python, NumPy and an option between TensorFlow and PyTorch. The development environment document contains details of the supported development environment, though it is not mandatory.

2. Tutorials

Quick start

Create a micromamba environment comp0197 and install PyTorch and/or TensorFlow:

micromamba create --name comp0197 python=3.12 -y 
micromamba activate comp0197 
pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu 
pip install tensorflow-cpu 

Go to a tutorial folder and run the training script:

cd path/to/tutorial
python train_pt.py
# or
python train_tf.py

Notes:

• Each tutorial folder has its own readme with any extra dependencies or data.
• *_pt.py scripts use PyTorch, *_tf.py scripts use TensorFlow 2.
• Visual outputs are saved to files, no GUI required.

Convolutional neural networks

Image classification
Image segmentation

Recurrent neural networks

Text classification
Character generation

Transformers

Language modelling

Variational autoencoder

MNIST generation

Generative adversarial networks

Face image simulation

3. Reading list

A collection of books and research papers is provided in the Reading List.