How to create normal distributed random numbers in Prolog?

Question

I am new to Prolog. And I am wondering how to create normal distributed random numbers in Prolog?
What I know uses “maybe” from the library (random) can establish probabilities. But what does the distribution problem have to do with this?

Answer 1

In general, languages ​​provide you with a uniform distribution from 0 to 1. There are various algorithms for getting from this uniform distribution to another distribution, but this case is especially common, so there are several ways to do this.

If you need a small number of random values ​​in a normal distribution, Box-Muller transform is a very simple algorithm, it is equal to a little math in several uniform random values:

random_normal(N) :- random(U1), random(U2), Z0 is sqrt(-2 * log(U1)) * cos(2*pi*U2), Z1 is sqrt(-2 * log(U1)) * sin(2*pi*U2), (N = Z0 ; N = Z1). 

This algorithm uses two identical values ​​and creates two normal values. I provide both solutions. Other ways to do this may be better for some applications. For example, you can use asserta/1 and retract/1 to cache the second value and use it without calculation, although the clutter in the dynamic storage can be about as bad as for other work (you would need to compare it). :

 ?- random_normal(Z). Z = -1.2418135230345024 ; Z = -1.1135242997982466. ?- random_normal(Z). Z = 0.6266801862581797 ; Z = -0.4934840828548163. ?- random_normal(Z). Z = 0.5525713772053663 ; Z = -0.7118660644436128. 

I'm not very sure about this, but it can lead you to a hump.

Answer 2

If you use SWI-Prolog or SWISH, then another option would be to use the built-in r, which will give you more flexibility with statistics and probabilities.

http://swish.swi-prolog.org/example/Rserve.swinb

http://www.swi-prolog.org/pack/list?p=real