Neural Network Optimization Based on Complex Network Theory: A Survey

Complex network science is an interdisciplinary field of study based on graph theory, statistical mechanics, and data science. With the powerful tools now available in complex theory for topology, it obvious that topology models can be applied to enhance artificial neural models. In this paper, we provide overview most important works published within past 10 years topic theory-based optimization methods. This review up-to-date optimized systems reveals fusion networks improves both accuracy robustness. By setting out our findings here, seek promote a better understanding basic concepts offer deeper insight into various research efforts have led use today.