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

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

38 Downloads (Pure)

Abstract

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.
Original languageEnglish
Title of host publicationPre-Proceedings of the 11th International Workshop on Neural-Symbolic Learning and Reasoning NeSy’16
EditorsTarek R. Besold, Luis Lamb, Luciano Serafini, Whitney Tabor
Place of PublicationNew York, NY
Number of pages11
Publication statusPublished - 16 Jul 2016
Event11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016 - The New School, New York, United States
Duration: 16 Jul 201617 Jul 2016
Conference number: 11

Conference

Conference11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016
Abbreviated titleNeSy
CountryUnited States
CityNew York
Period16/07/1617/07/16

Keywords

  • Learning
  • Neural blackboard architecture
  • In situ concepts
  • Reasoning
  • Reservoir
  • Wilson-Cowan dynamics

Fingerprint Dive into the research topics of 'Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning'. Together they form a unique fingerprint.

  • Cite this

    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.