Machine Learning for Economics and Finance in TensorFlow 2: Deep Learning Models for Research and Industry

© Isaiah Hull 2021

I. HullMachine Learning for Economics and Finance in TensorFlow 2https://doi.org/10.1007/978-1-4842-6373-0_9

9. Generative Models

Isaiah Hull¹  

(1)

Nacka, Sweden

 

Machine learning models can be divided into two categories: discriminative and generative. Discriminative models are trained to perform classification or regression. That is, we input a set of features and expect to receive probabilities of class labels or predicted values as outputs. In contrast, generative models are trained to learn the underlying distribution of the data. Once we have trained a generative model, we can use it to produce new examples of a class. Figure 9-1 illustrates the difference between the two categories of model.

Figure 9-1

Comparison of discriminator ...