Deep Learning Quick Reference

How to plan a machine learning problem

When building a new neural network, I recommend following the same basic steps every time.

Deep neural networks can get very complicated, very quickly. A little bit of planning and organization and greatly accelerate your workflow!

The following are the steps for building a deep neural network:

1. Outline the problem you're trying to solve.
2. Identify the inputs and outputs of the model.
3. Choose a cost function and metrics.
4. Create an initial network architecture.
5. Train and tune the network.