Machine Learning

Machine Learning covers methods for building models from data. This category addresses problem formulation, information preparation and evaluation without confusing performance on an example with reliability in a real setting. A useful approach starts with a clear objective and an appropriate way to measure errors.

Studying machine learning requires separating training from evaluation and comparing the model with a simple baseline. Exercises should examine data quality, possible bias and limits to generalisation. Check the programming and statistical prerequisites, and whether the programme addresses the kind of problem you need to solve.

Learning benefits from small examples, expected results and repeatable tests. Reading an error message, isolating a cause and explaining a decision are as important as completing an execution. Keep documentation aligned with the work and make the reasoning understandable to another person.

Check prerequisites, the programme, the version studied and availability with OO2 before selecting a session.

Training related to Machine Learning