TensorFlow For Machine Intelligence: A hands-on introduction to learning algorithms by Sam Abrahams & Danijar Hafner & Erik Erwitt & Ariel Scarpinelli

Author:Sam Abrahams & Danijar Hafner & Erik Erwitt & Ariel Scarpinelli [Abrahams, Sam]
Language: eng
Format: epub
Publisher: Bleeding Edge Press
Published: 2016-07-22T22:00:00+00:00

Common Layers

For a neural network architecture to be considered a CNN, it requires at least one convolution layer (tf.nn.conv2d). There are practical uses for a single layer CNN (edge detection), for image recognition and categorization it is common to use different layer types to support a convolution layer. These layers help reduce over-fitting, speed up training and decrease memory usage.

The layers covered in this chapter are focused on layers commonly used in a CNN architecture. A CNN isn’t limited to use only these layers, they can be mixed with layers designed for other network architectures.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.