Detection of contradictions in a semantic neural network

Connectionism is one of several models that explain how the brain might encode information. It implies that any cognizable entity and concept could be represented by a node. Central to the brain´s function is the concept of `contradiction´, which enables the brain to evaluate new concepts against recorded ones. This article deals with representing `contradiction´ in a semantic neural network. Three kinds of contradictions and ways of representing and detecting them are described. The model suggests that temporal encoding might be an important mechanism in detecting contradictions by the brain