Python Deep Learning Projects

Chapter 8 – Handwritten Digit Classification Using ConvNets

This chapter reminds us of the first deep neural net we created in Chapter 2, Training NN for Prediction Using Regression, and the business use case to which it was applied. The purpose of that chapter was to provide a foundation for our understanding of deep neural networks and how they operate. The complexity of the math underlying deep learning was highlighted when we compared the model architecture with the more advanced techniques afforded when we build deeper and more robust models. Complexity isn't cool just because it's complex; in this case, it's cool because of the improvement in realized performance utility that it provides. 

We spent a considerable amount of time examining ...