The aim of this module is to familiarise students with the whole pipeline of processing, analysing, presenting and making decisions using data. This is a research-led, MSc level course, where students are expected to develop a complete end-to-end data science application. The course blends data analysis, decision making and visualisation with practical python programming. The module assumes a reasonable programming background and is not suitable for students without prior programming experience. We are going to use Python programming in this module.
The aim of this module is to equip students with the theoretical tools and practical understanding necessary to create end-to-end data science applications, all the way from the initial concept to final deliverable.
Key Python libraries for this modules are: NumPy, Pandas, scikit-learn, Tensorflow, Keras, Matplotlib, and Seaborn.
For running the codes, I would highly recommend using Google Colab. Colaboratory is a Google research project created to help disseminate machine learning education and research. It’s a Jupyter notebook environment that requires no setup to use and runs entirely in the cloud. This means that as long as you have a Google account, you can freely train your models on a K80 GPU.
After completing this module, students will be expected to:
Understand the basics of the python data science and decision making
Summary and re-sampling statistics (cross-validation, permutation tests, bootstrapping).
Predictive Modelling and related methods
Data Exploration: Clustering methods, Dimensionality Reduction, Data Transformation
Deep Learning for Images and Text (Convolution Neural Networks and Recurrent Neural Networks)
Dataset Shift and Transfer Learning
Generative Models: Variational Auto-Encoders (VAEs) and Generative Adversarial Networks (GANs)
To be announced
I am sharing this module with Dr Ana Matran-Fernandez. First five lectures will be taken by Dr Ana Matran-Fernandez.
Lab work is available GitHub
Teaching Materials Available via Moodle