There are three key parts to most machine learning classifiers, which are as follows:

• The training pipeline
• The neural network setup and training outputs
• The usage pipeline

The training pipeline obtains data, stages it, cleanses it, homogenizes it, and puts it in a format acceptable to the neural network. Do not be surprised if the training pipeline takes 80% to 85% of your effort initially—this is the reality of most machine learning work. Generally, the more realistic the training data, the more time spent on the training pipeline. In enterprise settings, the training pipeline might be an ongoing effort being enhanced perpetually. This is especially true as datasets get larger.

The second part, the neural network setup, and training, can be quick for routine problems and can be a research-grade effort for harder problems. You may find yourself making small changes to the network setup, over and over, until you finally achieve the desired classifier accuracy. The training is the most computationally expensive part, so it takes time before you can evaluate the result of each incremental modification.

Once the initial setup is complete and the network is trained to a sufficient level of accuracy, we can just use it over and over. In Chapter 10, Go Live and Go Big, we'll explore more advanced topics, such as continuous learning, where even usage can feed back into further training the classifier.