A neuro-fuzzy system is a learning machine that finds the parameters of a fuzzy system using approximate techniques of neural networks. Both neural network and fuzzy system have common features. These can solve problems that there is no mathematical model for them. Adaptive Neuro-Fuzzy Inference System (ANFIS) is an adaptive network that uses supervised learning on learning algorithm. Selecting optimization method in training, to achieve effective results with ANFIS is very important. Heuristics and metaheuristics algorithms attempt to find the best solution out of all possible solutions of an optimization problem. ANFIS training can be based on non-derivative algorithms. Heuristics and metaheuristics are non-derivative algorithms that can lead to better performance in ANFIS training. Most heuristic and metaheuristic algorithms are taken from the behavior of biological systems or physical systems in nature. The newly released Emperor Penguins Colony (EPC) algorithm is a population-based and nature-inspired metaheuristic algorithm. This algorithm has many potential for solving various problems. In this paper an optimized ANFIS based on newly EPC algorithm is proposed. The optimized ANFIS is compared with other non-derivative algorithms on benchmark datasets. Eventually, the proposed algorithm is used to solve the classical inverted pendulum problem. The results show that the proposed ANFIS based on EPC algorithm has less error and better performance than other state-of-the-art algorithms in both training and testing phase.