Knowledge-increasable learning behaviors research of neural field

In a hierarchical set of systems, a lower order system is included in the parameter space of a large one as a subset. Such a parameter space has rich geometrical structures that are responsible for the dynamic behaviors of learning. Based on the theoretical analysis of information geometry and differential manifold, this paper studies knowledge-increasable learning behaviors of the neural field, and presents a layered knowledge-increasable artificial neural network model which has the knowledge-increasable and structure-extendible ability. The method helps to provide an explanation of the transformation mechanism of human´s recognition system and understand the theory of global architecture of neural networks.