ABSTRACT
Convolutional neural networks are a type of neural network that can learn local spatial patterns. They essentially perform feature extraction, which can then be used efficiently in later layers of a network. Their simplicity and fast running time, compared to models like LSTMs, makes them excellent candidates for supervised models for text. Neural networks such as CNNs have hyperparameters that you can tune, much like you tune the hyperparameters of more straightforward machine learning models. You can use algorithms for observation-level or local feature importance like LIME to explain predictions for individual examples in your data set, even for “black box” models like neural networks including CNNs.
