Learning Data Mining with Python - Second Edition

Implementing deep neural networks

Implementing these deep neural networks can be quite challenging due to their size. A bad implementation will take significantly longer to run than a good one, and may not even run at all due to memory usage.

A basic implementation of a neural network might start by creating a node class and collecting a set of these into a layer class. Each node is then connected to a node in the next layer using an instance of an Edge class. This type of implementation, a class-based one, is good to show how networks operate but too inefficient for larger networks. Neural networks simply have too many moving parts for this strategy to be efficient.

Instead, most neural networks operations can be expressed as mathematical ...