Machine Learning with Core ML: An iOS developer's guide to implementing machine learning in mobile apps by Joshua Newnham

Author:Joshua Newnham [Newnham, Joshua]
Language: eng
Format: epub
Tags: COM044000 - COMPUTERS / Neural Networks, COM004000 - COMPUTERS / Intelligence (AI) and Semantics, COM037000 - COMPUTERS / Machine Theory
Publisher: Packt Publishing
Published: 2018-06-27T23:00:00+00:00

This flat representation misses an important property of a CNN, which is how, after each subsequent pair of convolution and pooling layers, the input's width and height reduce in size. The consequence of this is that the receptive field increases depth into the network; that is, deeper layers have a larger receptive field and thus capture higher level features than shallower layers.

To better illustrate what each layer learns, we will reference the paper Visualizing and Understanding Convolutional Networks, by Matthew D. Zeiler and Rob Fergus. In their paper (previously referenced), they pass through images from their training set to identify the image patches that maximize each layer's activations; by visualizing these patches, we get a sense of what each neuron (hidden unit) at each of the layers learns. Here is an screenshot showing some of these patches across a CNN:

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.