In Swahili, Kujenga means to build. This course teaches how to use mathematical models and AI to build understanding of the world around us. But it also builds your own skills, by working on real world examples. Here you will learn how to establish statistical relationships between health and happiness; understand how to model disease outbreaks; test hypotheses about the fastest runners in the world; and how Google became so rich and powerful.

The course takes six weeks to complete, assuming 6-8 hours of work per week, for a student at (or nearing the end) of an undergraduate degree in a quantitative subject, like computer science, physics, mathematics, economics, bioinformatics, engineering, or similar. Completing this course means that you are considered ‘PhD ready’ for the Doctoral School in Computational Thinking and AI. This doesn’t mean we give you a place on the PhD Programme, but it does mean that you have built the skills to apply.

We run this course in October every year. To participate you will need to find a study group. Local study groups are located in Nairobi, Lagos, Stellenbosch, Makarere, and Addis Ababa. If you are not near one of these locations, you can join an online study group. In either case, you need to fill in the following form to apply to join.

Experience with programming is required, but we have added a section to get you started there too. Many of the examples include code in Python. We recommend you either download Anaconda and run the code in Spyder (download .py files). or upload the Python Notebook (download .ipynb files) Google Colab.

Contents

Are healthier people happier people?

• What you will learn
• Differentiation
• A line through the data
• Finding the best fit line
• Interpretting the data
• Exercise: look for other predictors of happiness
• Using regression in applications

Can we predict a disease outbreak?

• The SIR model
• Phase Planes
• The SEIR model

Are Ethiopian or Kenyan runners the fastest?

• What you will learn
• Why Do We Need a Test at All?
• Calculating the t-Statistic by Hand
• Doing it in Python

How did Google make billions of dollars?

• What you will learn
• The Mathematics of the PageRank algorithm
• Working with matrices in Python
• Simulating PageRank
• Eigenvalues and eigenvectors of a matrix
• Directly computing the PageRank scores

**This course was supported by the Equal Opportunities Group at the Information Technology Department, Uppasala University **