“…[1][2][3][4][5] Neural networks usually possess the characteristics of adaptivity, nonlinearity, parallelism and distributed storage, which can be used to solve the complicated problems that can not be solved by other approaches. [6][7][8][9] Specifically, the applications of neural networks including (but not limited to) the pattern classification, [10,11] deep learning, [12,13] approximation and prediction, [14,15] image processing, [16,17] machine learning, [18,19] optimization and computation, [20,21] complex system control [22][23][24] (including the robot system control). [25,26] Due to the extensive and significant applications of neu-ral networks, the development and investigation of neural networks have become common and heated topics for the researchers in biology, mathematics, physics, and computer science.…”