부산대학교 도서관

The neutral network further development is restricted in the system to some extent. The 3 layers RBF neutral network has the ability that self-study and self-remember, but sometimes because of serious multi-correlation between the variables, and a few observations while many variables, there usually will result into paralyzing in study. The partial least square regression has its advantage of building the calculation model between the variables with strong multi-correlation, especially much effective on a few data and many variables. So a new and effective method-improved neutral network has been introduced. The neutral network based on the partial least square regression. The results of example show the improved method has a few calculations and high accuracy, and provide a new way for valuing the rock mass strength parameters. Its network has been applied extensively.