Procedural knowledge processing based on area representation using a neural network

In this paper, a neural network is proposed which can deal with procedural knowledge based on area representation. The area representation expresses information by a group of neurons. Since it can be considered as a combination of localized representation and distributed representation, it has many advantages such as robustness, high efficiency for information representation, potential ability to treat similarity of data and so on. The proposed network based on area representation is constructed to store and recall procedural knowledge. We performed various kinds of computer simulations to examine the validity and effectiveness of the proposed network.