Skip to Content
Hands-On Mathematics for Deep Learning
book

Hands-On Mathematics for Deep Learning

by Jay Dawani
June 2020
Intermediate to advanced
364 pages
13h 56m
English
Packt Publishing
Content preview from Hands-On Mathematics for Deep Learning

Directed acyclic graphs

A DAG is a type of directed graph that doesn't have cycles in it. What this means is that there are no closed loops; that is, three or more nodes in a similar direction. So, suppose we have the following adjacency matrix:

We can see, in the preceding adjacency matrix, that we have an edge from node 1 to node 3, an edge from node 3 to node 4, and an edge from node 4 to node 1. This creates a cycle within the graph.

Visually, you can think of a DAG as having a hierarchy where nodes can flow downward or upward through subsequent levels. So, if our edges are all directed upwards, none of the nodes will ever point from ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Math for Deep Learning

Math for Deep Learning

Ronald T. Kneusel
Deep Learning with PyTorch

Deep Learning with PyTorch

Eli Stevens, Thomas Viehmann, Luca Pietro Giovanni Antiga

Publisher Resources

ISBN: 9781838647292