Automatic recognition of handwritten digits is an important problem, which can be found in many practical applications. In this section, we will implement a feed-forward network to address this.
To train, and test, the implemented models, we will be using one of the most famous datasets called MNIST of handwritten digits. The MNIST dataset is a training set of 60,000 examples and a test set of 10,000 examples. An example of the data, as it is stored in the files of the examples, is shown in the preceding figure.
The source images were originally in black and white. Later, to normalize them to the size of 20×20 pixels, intermediate brightness levels were introduced, due to the effect of the anti-aliasing filter for resizing. Subsequently, the images were focused in the center of mass of the pixels, in an area of 28×28 pixels, in order to improve the learning process. The entire database...