This course will cover the following topics:
1. Describing the data
Experiments and simulations generate large volumes of data. To make them useful and usable we have to summarise these into a few numbers or graphs. This session looks at how the raw numbers can be summarised into the final number(s) and plot(s) that go into a paper or a talk, and will look at how these are implemented in various software tools.
2. Fitting the data
Very often data is described by a model with one or more free parameters, which one needs to estimate. We look at how Maximum Likelihood estimation is used to do this, in examples ranging from the simple straight-line fit to complicated general functions.
3. Machine learning
Neural networks can be used to discriminate between different event types. We look at them in detail (and also more briefly at other techniques and other uses) and their implementation, including training and testing and measuring performance.
On each of the three days of the course there will be a lecture at 10:00 am and a workshop at 11:45 am. Students will work in groups on problems and exercises presented during the lectures. Each day will be completed by a review and discussion session at 2:00 pm.