Fig. 1
From: Computer-aided imaging analysis in acute ischemic stroke – background and clinical applications
a A Venn diagram presenting that deep learning is a type of representation learning, which is a kind of machine learning, which is a subfield of Artificial intelligence (adapted from [8]). b A summarised representation of the most common machine learning algorithms and models. Sup L: Supervised learning: labelled data is used. Unsup L: Unsupervised learning: unlabeled data is used. Semi-supervised learning: a mixture of supervised and unsupervised learning. Reinf L: Reinforcement learning: learning by doing (rewarding correct- and punishing wrong actions). Rep L: Representation learning: automatic generation of features. DL: Deep learning: hierarchical representation learning