In this paper, a neural network which can treat the procedural knowledge based on the area representation is proposed. The area representation expresses information by a group of neurons. Since it can be considered as a combination of the localized representation and the 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 the area representation is constructed to store and recall the procedural knowledge. We performed various kinds of computer simulations to examine the validity and effectiveness of the proposed network.
|Proceedings of the IEEE International Conference on Systems, Man and Cybernetics
|Published - 1997 12月 1
|Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 1 (of 5) - Orlando, FL, USA
継続期間: 1997 10月 12 → 1997 10月 15
ASJC Scopus subject areas