Data Science Courses

The general skills module includes the following lectures:

Python introduction (Andrew Cooper)

This course gives a quick introduction to python, it covers:

  • Python syntax
  • Collections and loops
  • Input and output
  • Functions and classes
  • Plotting and scientific computing libraries

Introductory Statistics (8 lectures + workshop, presented by Ifan Hughes)

This course provides the foundation in statistics needed for the other courses.  Its syllabus includes

  • Review of elementary statistical concepts
  • Central Limit Theorem
  • Functional approach to error propagation
  • Weighted least squares fitting
  • Least-squares fitting of complex functions
  • Computer minimisation and the error matrix
  • Hypothesis testing—how good are our models?

Introduction to Numerical Methods (8 lectures, 4 drop-in sessions, one project)

This course gives an introduction to numerical methods, based on the book by Giordano and Nakanishi (G&N). In the first part we focus on construction and implementation of basic algorithms in python. In the second part we will use a compiled language to implement numerical methods.  The course is assessed through homework and the project.

  • Discretization and discretization error (G&N, Chapter 1)
  • Solving differential equations: Runge-Kutta method (G&N, Chapter 2)
  • Chaos (G&N, Chapter 3)
  • Potential and Fields (G&N, Chapter 5)
  • Waves (G&N, Chapter 6)
  • Root finding and integration (G&N, Appendix B)
  • Introductory Monte Carlo method: Random walks and percolation (G&N, Chapter 7)
  • Statistical Mechanics and the Ising model (G&N, Chapter 8)

For the project the students were invited to chose a topic in the book but outside the lectures of the course.

Introduction to Machine Learning (8 lectures, 4 drop-in sessions)

The intruduction to machine learning course provides a basic overview of machine learning techniques with practical exercises using scikit-learn.

  • Classification vs regression
  • Linear and logistic regression
  • Model selection: overfitting and regularisation
  • ROC curves
  • Decision trees
  • Neural networks
  • Unsupervised learning: k-nearest neighbours

Introduction to High-Performance Computing

Generic Skills components

  • ILM-acrredited 2-weeks mini-MBA provided by the Durham Business School
  • 3-days workshop on “Communicating Science” provided by the Durham Science Faculty outreach team.
  • A series of seminars and presentations by our partners
  • 8 weeks team project