Interpretable AI

Part 3. Interpreting model representations

This part of the book continues to focus on black-box models, but focuses specifically on understanding what features or representations have been learned by them.

In chapters 6 and 7, you’ll learn about convolutional neural networks and neural networks used for language understanding. You will learn how to dissect the neural networks and understand what representations of the data are learned by the intermediate or hidden layers in the neural network. You’ll also learn how to visualize high-dimensional representations learned by the model using techniques like principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE).