MATLAB Machine Learning by Michael Paluszek & Stephanie Thomas

Author:Michael Paluszek & Stephanie Thomas
Language: eng
Format: epub
Publisher: Apress, Berkeley, CA

The training function also outputs the training error as the net evolves and the root-mean-square (RMS) of the error.

Figure 9.6Single-digit training error and RMS error.

Since we have a large number of input neurons, a line plot is not very useful for visualizing the evolution of the weights for the hidden later. However, we can view the weights at any given iteration as an image. Figure 9.7 shows the weights for the network with 30 nodes after training visualized using imagesc. We may wonder if we really need all 30 nodes in the hidden layer, or if we could extract the necessary number of features identifying our chosen digit with fewer. In the image on the right, the weights are shown sorted along the dimension of the input pixels for each node; we can clearly see that only a few nodes seem to have much variation from the random values they are initialized with. That is, many of our nodes seem to be having no impact.

Figure 9.7Single-digit network, 30-node hidden layer weights. The image on the left shows the weight value. The image on the rights shows the weights sorted by pixel for each node.

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.