Weather forecasting with Markov chains

We want to build a statistical model to predict the weather. To simplify the model, we will assume that there are only two states: sunny and rainy. Let's further assume that we have made some calculations and discovered that tomorrow's time is somehow based on today's time, according to the following transition matrix:

Recall that this matrix contains the conditional probabilities of the type expressed as P (A | B)—that is, the probability of A given B. So, this matrix contains the following conditional probabilities:

In the preceding matrix, Su = sunny and Ra = rainy. Each row must consist of a complete ...

Get Keras Reinforcement Learning Projects now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.