Skip to main content

Data Science & Machine Learning

Pre-requisites

Completion of the Computational Statistics with Python (CSP) module or equivalent prior experience


Introduction

This module aims to enable participants to select, implement and evaluate machine learning algorithms in data science. In particular, the module highlights several of the most common, and in-demand, modern algorithms including Stochastic Gradient Decent, ensemble methods and deep learning. Alongside technical knowledge, participants should develop an understanding of the applicability of different types of machine learning to common problems, and best practice for data science and Big Data analytics projects.


Objectives

Upon successful completion participants will be able to:

  1. Interpret and evaluate various use-cases and the applicability of data science and machine learning.
  2. Comprehensive understanding of best practices for data processing and feature engineering.
  3. Implement, interpret and critique current, professional standard learning models.
  4. Automate deployment-ready data science pipelines and algorithms.
  5. Evaluate and interpret the results of machine learning models and tune them to optimise performance.
  6. Comprehension of the core topics of data science, machine learning and artificial intelligence.


Syllabus

  • Data Science Foundations
    - Core concepts of Data Science & Machine Learning
    - Data pre-processing & feature engineering
  • Classification
    - Theoretical background
    - Naïve Bayes
    - Decision Trees
    - Support Vector Machines
    - Model selection and evaluation
  • Regression
    - Theoretical background
    - Linear models
    - Ridge Regression
    - Lasso Regression
    - Stochastic Gradient Decent
    - Model selection and evaluation
  • Ensemble Methods
    - Bagging
    - Boosting
    - Stacking
  • Deep Learning
    - Artificial Neural Networks
    - Deep Neural Networks
    - Long-Short Term Memory
    - Model training and evaluation


Assessment

4000 Words Post Module Assessment (60 hours, 75% weighting) and In-class Presentation (1.5 hours, 25% weighting)


Duration

1 week, to include lectures, seminars, workshops and presentations, approximately 36 total contact hours.