This time a year ago, I was translating Paul Graham's "Hacker and painter".
The eighth chapter of the book, which wrote a very specific technical question----How to use Bayesian inference to filter spam (English version).
I didn't fully understand the chapter. At that time was to bite the bullet and literally translate it. Although the quality of the translation is OK, but the heart is very uncomfortable, determined to make sure to understand it.
A year later, I read some of the probabilistic literature, and gradually found that Bayesian inference is not difficult. The principle part is fairly easy to understand and does not require advanced mathematics.
Here is my study notes. The need to declare that I am not an expert in this field, mathematics is actually my weakness. Welcome everyone to put forward valuable advice, let us learn and improve together.
=====================================
Bayesian inference and its application in Internet
Author: Ruan Yi Feng
One, what is Bayesian inference
Bayesian inference (Bayesian inference) is a statistical method used to estimate the properties of a statistic.
It is the application of Bayesian theorem (Bayes ' theorem). Thomas Bayes, a British mathematician, first proposed the theorem in a paper published in 1763. Thomas Beyes
Bayesian inference is quite different from other statistical inference methods. It is based on subjective judgments, that is, you can estimate a value without the need for objective evidence, and then revise it according to the actual result. It is because of its subjectivity is too strong, has been criticized by many statisticians.
Bayesian inference requires a lot of computation, so it has been a long time in history and cannot be widely used. Only after the birth of the computer, it will receive real attention. It has been found that many statistics cannot be objectively judged in advance, and the large datasets appearing in the internet era, combined with the high speed computing power, provide convenience for validating these statistics and create conditions for applying Bayesian inference, and its power is becoming increasingly apparent.