Abstract

Objectives: To analyse the layers in Convolutional Neural Network in the context of text recognition looking for interpretations. Methods/Analysis: Through the training of a deep Convolutional Neural Network and its application to the recognition of numerical characters from the MNIST dataset, the characteristics of deep architectures are studied and analysed. Making a detailed study of the behaviour of the different weights and their significance through the training of the network using - images, error values and gradient values which characterize each of the layers. Findings: After the training it is observed that the convolution layers have a possible interpretation. Results were obtained from the images of the MNIST dataset after going through the convolution layers with images and random filters. However, the most representative results are achieved by viewing a single image using random filters. Improvement: Recommendations for design and implementation based on the example and other references are presented.

References

Download PDF
Back