Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning

Simulations are presented and discussed of learning sequential control in a Neural Blackboard Architecture (NBA) for in situ concept-based reasoning. Sequential control is learned in a reservoir network, consisting of columns with neural circuits. This allows the reservoir to control the dynamics of processing by responding to information given by questions and the activations in the NBA. The in situ nature of concept representation directly influences the reasoning process and learning in the architecture.