Нашли опечатку? Выделите ее мышкой и нажмите Ctrl+Enter
Название: Reductions of Hidden Information Sources
Авторы: Ay N., Crutchfield J.P.
Аннотация:
Journal of Statistical Physics, Vol. 120, Nos. 3/4, August 2005. p. 659-684.
DOI: 10.1007/s10955-005-6797-4
In all but special circumstances, measurements of time-dependent processes reflect internal structures and correlations only indirectly. Building predictive models of such hidden information sources requires discovering, in some way, the internal states and mechanisms. Unfortunately, there are often many possible models that are observationally equivalent. Here we show that the situation is not as arbitrary as one would think...