Pattern-Based Reasoning System Using Self-incremental Neural Network for Propositional Logic

  • Authors:

  • Akihito Sudo;Manabu Tsuboyama;Chenli Zhang;Akihiro Sato;Osamu Hasegawa

  • Affiliations:

  • Dept. of Computer Intelligence and Systems Science, Tokyo Institute of Technology Imaging Science and Engineering Lab., Tokyo Institute of Technology, Midori-ku, Japan;Dept. of Computer Intelligence and Systems Science, Tokyo Institute of Technology Imaging Science and Engineering Lab., Tokyo Institute of Technology, Midori-ku, Japan;Dept. of Computer Intelligence and Systems Science, Tokyo Institute of Technology Imaging Science and Engineering Lab., Tokyo Institute of Technology, Midori-ku, Japan;Dept. of Computer Intelligence and Systems Science, Tokyo Institute of Technology Imaging Science and Engineering Lab., Tokyo Institute of Technology, Midori-ku, Japan;Dept. of Computer Intelligence and Systems Science, Tokyo Institute of Technology Imaging Science and Engineering Lab., Tokyo Institute of Technology, Midori-ku, Japan

  • Venue:
  • Neural Information Processing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose an architecture for reasoning with pattern-based if-then rules that is effective for intelligent systems like robots solving varying tasks autonomously in a real environment. The proposed system can store pattern-based if-then rules of propositional logic, including conjunctions, disjunctions, negations, and implications. The naive pattern-based reasoning can store pattern-based if-then rules and make inferences using them. However, it remains insufficient for intelligent systems operating in a real environment. The proposed system uses an algorithm that is inspired by self-incremental neural networks such as SONIN and SOINN-AM in order to achieve incremental learning, generalization, avoidance of duplicate results, and robustness to noise, which are important properties for intelligent systems