In this chapter, we introduced DL as a form of representation learning that extracts hierarchical features from high-dimensional, unstructured data. We saw how to design, train, and regularize feedforward neural networks using NumPy. We demonstrated how to use the popular DL libraries Keras, PyTorch, and TensorFlow, which are suitable for use cases from rapid prototyping to production deployments.
In the next section, we will explore CNNs that are particularly well suited for image data and other data sources where local patterns matter.
