The paper presents a connectionist framework that is capable of representing and learning
propositional knowledge. An extended version of propositional calculus is developed and is …

The paper focuses on the problem of rule extraction from neural networks, with the aim of
transforming the knowledge captured in a trained neural network into a familiar form for …

Abduction is the process of proceeding from data describing a set of observations or events,
to a set of hypotheses which best explains or accounts for the data. Cost-based abduction …

The question of satis ability for a given propositional formula arises in many areas of AI.
Especially nding a model for a satis able formula is very important though known to be NP …

This paper proposes a method of rule extraction from ordinary backpropagation neural
networks, which do not have a structure that facilitates rule extraction. This method is based …

Artificial bee colony (ABC) is a relatively new swarm intelligence method that solves the
various type of optimization problems. This algorithm utilized the behavior of the actual bees …

From its beginning, research in the field of connectionist systems 1 has always been
concerned with the integration of symbolic and connectionist computation (McCulloch and …

The representation and learning of a first-order theory using neural networks is still an open
problem. We define a propositional theory refinement system which uses min and max as its …

Neural networks have been criticized for their lack of human comprehensibility. First, this
paper proposes an extraction method of crisp if-then rules from ordinary backpropagation …

Ausgangspunkt der Uberlegungen war die Fragestellung, inwieweit spezielle
algorithmische Probleme aus dem Bereich der Molekularbiologie in geeignet kodierter Form …