Skip to Main Content
Hands-On Java Deep Learning for Computer Vision
book

Hands-On Java Deep Learning for Computer Vision

by Klevis Ramo
February 2019
Intermediate to advanced content levelIntermediate to advanced
260 pages
6h 3m
English
Packt Publishing
Content preview from Hands-On Java Deep Learning for Computer Vision

Multiclass classification

So far, we've seen multiple activation functions, but the one thing that remains constant is the limitation that they can provide only two classes, 0 or 1. Consider the heart disease example:

The neural network predicted 15% not having heart disease and 85% having heart disease, and we set the threshold to 50%. This implies that as soon as one of these percentages exceeds the threshold, we output its index, which would be 0 or 1. In this example, obviously 85% is greater than 50%, so we will output 1, meaning that this person will not have heart disease in the future.

These days, neural networks can actually predict ...

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

Java Deep Learning Projects

Java Deep Learning Projects

Md. Rezaul Karim
Hands-On Computer Vision with TensorFlow 2

Hands-On Computer Vision with TensorFlow 2

Benjamin Planche, Eliot Andres

Publisher Resources

ISBN: 9781789613964Supplemental Content