Skip to Main Content
Practical Convolutional Neural Networks
book

Practical Convolutional Neural Networks

by Mohit Sewak, Md. Rezaul Karim, Pradeep Pujari
February 2018
Intermediate to advanced content levelIntermediate to advanced
218 pages
5h 31m
English
Packt Publishing
Content preview from Practical Convolutional Neural Networks

CNN architectures and drawbacks of DNNs

In Chapter 2Introduction to Convolutional Neural Networks, we discussed that a regular multilayer perceptron works fine for small images (for example, MNIST or CIFAR-10). However, it breaks down for larger images because of the huge number of parameters it requires. For example, a 100 × 100 image has 10,000 pixels, and if the first layer has just 1,000 neurons (which already severely restricts the amount of information transmitted to the next layer), this means 10 million connections; and that is just for the first layer.

CNNs solve this problem using partially connected layers. Because consecutive layers are only partially connected and because it heavily reuses its weights, a CNN has far fewer parameters ...

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

Understanding Convolutional Neural Networks (CNNs)

Understanding Convolutional Neural Networks (CNNs)

Nell Watson
Practical Machine Learning for Computer Vision

Practical Machine Learning for Computer Vision

Valliappa Lakshmanan, Martin Görner, Ryan Gillard

Publisher Resources

ISBN: 9781788392303Supplemental Content