Detecting patterns in the hidden layer

The job of the neurons in the hidden layer is to learn to detect patterns within the input data. In our case, the neurons in the hidden layer(s) will detect the presence of certain substructures that constitute a wider symbol. This is illustrated in Figure 7.7, where we assume that the first three neurons in the hidden layer learn to recognize forward slash, back slash and horizontal line type patterns respectively:

Figure 7.7: Neurons in the hidden layer detect patterns and substructures

Get Machine Learning with Apache Spark Quick Start Guide now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.