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

Frank van der Velde

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

Frank van der Velde

Faculty of Behavioural, Management and Social Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic

164 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 language	English
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

Conference	11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016
Abbreviated title	NeSy
Country/Territory	United States
City	New York
Period	16/07/16 → 17/07/16

Keywords

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

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

VanderVelde2016learningFinal published version, 1.22 MB
NeSy 2016 Pre-proceedingsFinal published version, 9.21 MB

Cite this

@inproceedings{839df341a53348f4ae80937781d10aea,

title = "Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning",

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.",

keywords = "Learning, Neural blackboard architecture, In situ concepts, Reasoning, Reservoir, Wilson-Cowan dynamics",

author = "{van der Velde}, Frank",

year = "2016",

month = jul,

day = "16",

language = "English",

editor = "Besold, {Tarek R.} and Luis Lamb and Luciano Serafini and Whitney Tabor",

booktitle = "Pre-Proceedings of the 11th International Workshop on Neural-Symbolic Learning and Reasoning NeSy{\textquoteright}16",

note = "11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016, NeSy ; Conference date: 16-07-2016 Through 17-07-2016",

}

van der Velde, F 2016, Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning. in TR 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, 11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016, New York, New York, United States, 16/07/16.

Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning. / van der Velde, Frank.
Pre-Proceedings of the 11th International Workshop on Neural-Symbolic Learning and Reasoning NeSy’16. ed. / Tarek R. Besold; Luis Lamb; Luciano Serafini; Whitney Tabor. New York, NY, 2016.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic

TY - GEN

T1 - Learning sequential control in a Neural Blackboard Architecture for in situ concept reasoning

AU - van der Velde, Frank

N1 - Conference code: 11

PY - 2016/7/16

Y1 - 2016/7/16

N2 - 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.

AB - 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.

KW - Learning

KW - Neural blackboard architecture

KW - In situ concepts

KW - Reasoning

KW - Reservoir

KW - Wilson-Cowan dynamics

M3 - Conference contribution

BT - Pre-Proceedings of the 11th International Workshop on Neural-Symbolic Learning and Reasoning NeSy’16

A2 - Besold, Tarek R.

A2 - Lamb, Luis

A2 - Serafini, Luciano

A2 - Tabor, Whitney

CY - New York, NY

T2 - 11th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2016

Y2 - 16 July 2016 through 17 July 2016

ER -

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

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this