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.
|Title of host publication||Pre-Proceedings of the 11th International Workshop on Neural-Symbolic Learning and Reasoning NeSy’16|
|Editors||Tarek R. Besold, Luis Lamb, Luciano Serafini, Whitney Tabor|
|Place of Publication||New York, NY|
|Number of pages||11|
|Publication status||Published - 16 Jul 2016|
|Event||11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016 - The New School, New York, United States|
Duration: 16 Jul 2016 → 17 Jul 2016
Conference number: 11
|Conference||11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016|
|Period||16/07/16 → 17/07/16|
- Neural blackboard architecture
- In situ concepts
- Wilson-Cowan dynamics
van der Velde, F. (2016). Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning. In T. R. Besold, L. Lamb, L. Serafini, & W. Tabor (Eds.), Pre-Proceedings of the 11th International Workshop on Neural-Symbolic Learning and Reasoning NeSy’16 New York, NY.