Probabilistic Deep Learning

2 Neural network architectures

This chapter covers

• Needing different network types for different data types
• Using fully connected neural networks for tabular-like data
• Using 2D convolutional neural networks for image-like data
• Using 1D convolutional neural networks for ordered data

The vast majority of DL models are based on one or a combination of three types of layers: fully connected, convolutional, and recurrent. The success of a DL model depends in great part on choosing the right architecture for the problem at hand.

If you want to analyze data that has no structure, like tabular data in Excel sheets, then you should consider fully connected ...