Controlling simple structural information to improve generalization performance

In this paper, new information called structural information is proposed. The structural information is used to control information in internal representations, and eventually to control the production of internal representations. By controlling the structural information, we can obtain appropriate internal representations, depending on given problems. The structural information methods were applied to the XOR problem in which the utility of structural information is shown. Then, we applied the methods to language acquisition problems complex enough to test the performance. Experimental results confirmed that generalization is not concerned with total information but with the second order information