Markov processes are stochastic processes with no memory. How are called the stochastic processes with full memory? Can't found anything on google.
Asked
Active
Viewed 611 times
1 Answers
1
I would look at Autoregressive or ARMA models. I'm not sure if they'll work like you want them to, but when you include memory in your model things get a lot more complicated. Instead of being independent of most values in the series, suddenly they're dependent on all of them and things get gradually more and more complex.
If you discuss a little more about what you're trying to model I may be able to give you a little bit more help.
Seth
- 105
-
Interesting. I'm developing a Computer Algebra System. It now has a set of math rules. I asigned a number to each rule. The problem is that there are more than 50 rules and it has to search through all of these until finds the correct one. What I'm trying to do is to give it the capability to learn and predict with certain chances what's the best math rule to apply next, based on all rules applied before. – gab06 Aug 20 '14 at 18:26
-
In other words, given a series of values (the numbers representing the math rules), try to predict future values. – gab06 Aug 20 '14 at 18:30
-
But I think I will use a bayesian network instead. This looks too complex for me. – gab06 Aug 20 '14 at 18:36