The notes are for the lectures and tutorials at the CERN School of Computing 2019. Questions and comments on these notes can be sent to Anna Scaife, or entered as an issue on the github repo.
Understanding Classification: train/val/test splits, decision trees and random forests
precision metrics, feature ranking, pulsar case study
Gaussian Process Modelling: imputing missing data, forward prediction
kernels, covariance matrices, imputation, forward prediction, optimization
Convolutional Neural Networks: hidden layers, standard architectures
data augmentation, radio galaxy case study, computational considerations
This webpage is inspired by the Stanford cs231n lecture course.