Over the last few decades, neural network (NN) has seen successful development that has wide applications due to the effort of industrial and academic communities. With the powerful approximation ability of NN, it has been evolved into many promising fields, such as modeling and identification of complex and nonlinear systems and optimization and automatic control.

Specifically, the state-of-the-art deep learning NN, allows richer intermediate representations to be learnt, eliminating the effort of feature engineering. For different theories and applications, the design philosophy of NN architecture can be different. Nevertheless, generally NN can be expressed as a weighted sum of several kernel functions, of which the weights can be tuned to approximate an arbitrary smooth or continuous nonlinear function. However, to reveal the fundamental representations and behaviors of NN as a complex system while it is applied into real-world control applications is still a problem to be explored. Understanding this problem could not only promote better understanding of the underlying mechanisms of NN, but also provide a possibility to design a universal NN solution in various real-world applications.

The main focus of this special issue will be on NN theory and analysis as well as its potential engineering applications in complex systems. Authors are invited to present theories, algorithms, and frameworks aimed at bringing about advanced techniques of NN for modeling, identification, control, and optimization of complex systems. We also encourage authors to introduce new results for synthesizing NN into complex psychical systems, such as, hypersonic flight vessels, robots, and industrial process.

Potential topics include but are not limited to the following:

• Convergence and stability analysis of neural network
• Neural network for optimization
• Neural network based system identification
• Neural network based observer design
• Theory and applications of recurrent neural network
• Theory and applications of deep learning neural networks
• Neural models of perception, action, and cognition
• Neural network control for mobile robots, flight vessels, autonomous underwater vehicles, and other robotic systems
• Neural network modeling and control for sustainable energy plants