When to use MLP, CNN, RNN Neural Networks?

What neural network is appropriate for your predictive modeling problem?

When to Use Multilayer Perceptrons?

• Tabular datasets
• Classification prediction problems
• Regression prediction problems.

The flexible allows them to be applied to other types of data. For example, the pixels of an image can be reduced down to one long row of data and fed into MLP. The words of document can also be reduced to one long row of data and fed into MLP. Even the lag observations for a time series prediction problem can be reduce to a long row of data and fed to a MLP.

Try MLPs on:

• Image data
• Text data
• Time series data
• Other types of data

When to Use Convolutional Neural Networks?

CNNs were designed to map image data to an output variable.

Use CNNs for:

• Image data
• Classification prediction problems
• Regression prediction problems

Try CNNs on:

• Text data
• Time series data
• Sequence input data

When to use Recurrent Neural Networks?

RNNs were designed to work with sequence prediction problems.

Use RNNs for:

• Text data
• Speed data
• Classification prediction problems
• Regression prediction problems
• Generative model

Don’t use RNNs for:

• Tabular data
• Image data

Perhaps try RNNs on:

• Time series data

References:

When to Use MLP, CNN, and RNN Neural Networks (machinelearningmastery.com)