Using Graphs to Model Problems, Part 1

Filters allow us to choose which features to use for our classification, so that we are basing our inferences on the most relevant information (e.g. teeth instead of body size for dietary habits of mammals).

A set of objects called nodes (or vertices) connected by a set of edges (or arcs).

A graph with unidirectional edges.

A graph in which each edge has an associated weight.

Edge has a source and destination, and is therefore unidirectional already. This makes it easier for us to treat the bidirectional case Graph (where there is an edge for each direction) as a special case of Digraph.