Toward Intelligent Systems: Calculi of Information Granules

  • Authors:
  • Andrzej Skowron

  • Affiliations:
  • -

  • Venue:
  • Proceedings of the Joint JSAI 2001 Workshop on New Frontiers in Artificial Intelligence
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an approach based on calculi of information granules as a basis for approximate reasoning in intelligent systems. Approximate reasoning schemes are defined by means of information granule construction schemes satisfying some robustness constraints. In distributed environments such schemes are extended to rough neural networks. Problems of learning in rough neural networks from experimental data and background knowledge are discussed. The approach is based on rough mereology.