Skip to Main Content
Innovation ability of Industrial clusters is an important measure of regional innovation. Industrial clusters with strong innovation ability can promote the development of innovative enterprises, which are the key element of regional innovation. Therefore, it is important to establish models to evaluate innovation ability for industry clusters. In this paper, an improved BP neural network model was proposed as a theoretical foundation for the evaluation of innovation ability of industrial clusters. Limitations with standard neural network model, such as tendency for error to stay at local minimum, slow convergence rate, etc, was improved with a gradient descent optimization method. The improved back propagation neural network model was utilized to evaluate innovation ability of major industrial clusters in Shenyang.