Deep Learning By Example by Ahmed Menshawy

Author:Ahmed Menshawy
Language: eng
Format: epub
Tags: COMPUTERS / Neural Networks, COMPUTERS / Machine Theory, COMPUTERS / Intelligence (AI) and Semantics
Publisher: Packt
Published: 2018-02-27T12:02:41+00:00

Output:

Accuracy on Test-Set: 92.8% (9281 / 10000)

Example errors:

Figure 9.13: Accuracy over the test

Confusion Matrix: [[ 971 0 2 2 0 4 0 1 0 0] [ 0 1110 4 2 1 2 3 0 13 0] [ 12 2 949 15 16 3 4 17 14 0] [ 5 3 14 932 0 34 0 13 6 3] [ 1 2 3 0 931 1 8 2 3 31] [ 12 1 4 13 3 852 2 1 3 1] [ 21 4 5 2 18 34 871 1 2 0] [ 1 10 26 5 5 0 0 943 2 36] [ 16 5 10 27 16 48 5 13 815 19] [ 12 5 5 11 38 10 0 18 3 907]]

The following is the output:

Figure 9.14: Confusion matrix of the test set.

It was interesting that we actually got almost 93% accuracy over the test while using a basic convolution network. This implementation and the results show you what a simple convolution network can do.

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.