concept complex distribution in category Keras

This is an excerpt from Manning's book Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability MEAP V06. Login to get full access to this book.

One way to model complex distributions are mixtures of simple distributions, such as Normal, Poisson, or Logistic distributions, which you know from the previous chapters. Mixture models are used in state-of-the-art networks like Google's parallel WaveNet or OpenAI’s PixelCNN++ to model the output.

Figure 6.12 A chain of simple transformations makes it possible to create complex transformations needed to model complex distributions. From right to left: Starting from a standard Gaussian distribution is transformed via successive transformations to a complex distribution with bimodal shape on the left side.