A New Neural Network Models Based for Rule-Based Reasoning

摘要

Neural Network models of rule-based reasoning are investigated and it is shown that while such models usually carry out reasoning in exactly the same way as symbolic systems, they have more to offer in terms of commonsense reasoning. CONSYDEER, is proposed to account for common sense reasoning patterns and to remedy the brittleness problem in traditional rule-based system. This work shows reasoning of connection models are not only implementation of their symbolic counterparts, but also computational models of commonsense reasoning.