The following coursework was developed to provide an in-depth theoretical understanding of Machine Learning (ML) models and inference using the models.
Coursework 1 focuses on theoretical ML with a huge emphasis on assumptions made by the models. Details of the work is in the file CW1-Models/report.pdf and is based on the questions in CW1-Models/questions-models.pdf.
Coursework 2 focuses on the implementation of a Markov Random Field with an Ising prior and the different ways of performing inference with the model (i.e. Gibbs Sampling vs a Variation Auto-encoder). Details of the work is in the file CW2-Inference/report.pdf and is based on the questions in CW2-Inference/questions-inference.pdf.