TY - JOUR AU - Peng, Zixiong AU - Chen, Xiaowei PY - 2014 DA - 2014/05/07 TI - Uncertain systems are universal approximators JO - Journal of Uncertainty Analysis and Applications SP - 13 VL - 2 IS - 1 AB - Uncertain inference is a process of deriving consequences from uncertain knowledge or evidences via the tool of conditional uncertain set. Based on uncertain inference, uncertain system is a function from its inputs to outputs. This paper proves that uncertain systems are universal approximators, which means that uncertain systems are capable of approximating any continuous function on a compact set to arbitrary accuracy. This result can be viewed as an existence theorem of an optimal uncertain system for a wide variety of problems. SN - 2195-5468 UR - https://doi.org/10.1186/2195-5468-2-13 DO - 10.1186/2195-5468-2-13 ID - Peng2014 ER -