Using a constructive interactive activation and competition neural network to construct a situated agent's experience

This paper presdents an approach that uses a Constructive Interactive Activation and Competition (CIAC) neural network to model a situated agent's experience. It demonstrates an implemented situated agent and its learning mechanisms. Experiments add to the understanding of how the agent learnds from its interactions with the environment. The agent can develop knowledge structures and their intentional descriptions (conceptual knowledge) specific to what it is confronted with - its experience. This research is presented within the design optimization domain.