chapter five

5 Connecting causality and deep learning

 

This chapter covers

  • Incorporating deep learning into a causal graphical model
  • Training a causal graphical model with a variational autoencoder
  • Using causal methods to enhance machine learning

The title of this book is Causal AI. How exactly does causality connect to AI? More specifically, how does causality connect with deep learning, the dominant paradigm in AI? In this chapter, I present two perspectives on how to think about this question:

  1. How to incorporate deep learning into a causal model (Section 5.1 and 5.2).
  2. How to use causal reasoning to do better deep learning (Section 5.3).

5.1 A causal model of a computer vision problem

5.1.1 Leveraging the universal function approximator

5.1.2 Causal abstraction and plate models

5.2 Training the neural causal model

5.2.1 Setting up the training data

5.2.2 Setting up the variational autoencoder

5.2.3 The training procedure

5.2.4 Evaluating training

5.2.5 How should we causally interpret Z?

5.2.6 Advantages of this causal interpretation

5.3 Using causal inference to enhance deep learning

5.3.1 Example: Independence of mechanism as an inductive bias

5.3.2 Case Study: Semi-supervised learning

5.3.3 Demystifying deep learning with causality

5.4 Summary