Bayes' theorem plays an important role in computational intelligence, a sub-field of artificial intelligence that's mainly concerned with a biologically-inspired approach to machine intelligence. Bayesian inference is often one of the pillars behind computational learning theory, and it works by applying concepts of statistical inference in such a way that, as more information becomes available, a hypothesis is repeatedly updated and perfected.
This project is heavily inspired by, and based on, the "An Introduction to Bayesian Thinking" book, which is available here: https://statswithr.github.io/book/. It contains regular markdown, LaTeX code for all mathematical calculations and R code that illustrates and/or applies some concepts in a practical way. The external packages used in this project are:
- caret: for classification and regression training (6.0-86);
- e1071: for the naive Bayes algorithm (1.7-4).
Personal notes and experiments are also included in this study.
Please note that covering all topics of Bayesian inference is a very daunting task, as it has connections to wildly different statistical subjects. Thus, most of the focus here is on exploring its impact solely on computational intelligence.