A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination

Alex Doboli; Simona Doboli

doi:10.1109/SSCI50451.2021.9660045

A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination

Alex Doboli
, Simona Doboli

Electrical Engineering

Stony Brook University

Hofstra University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Many modern applications require both modeling and generative capabilities, so that they can produce novel outcomes that address requirements beyond the solutions used in model training. Current AI approaches arguably emphasize modeling but pay much less attention to generative capabilities. This paper presents a new learning and response generating (LRG) agent-based model, in which interacting agents continuously learn symbolic - numeric knowledge and create new outcomes (responses) using a set of five ways to combine concepts. Each way has both fast, reactive and a slow, planned versions. Experiments present the characteristics of an agent's modeling and generating capabilities.

Original language	English
Title of host publication	2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728190488
DOIs	https://doi.org/10.1109/SSCI50451.2021.9660045
State	Published - 2021
Event	2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Virtual, Online, United States Duration: Dec 5 2021 → Dec 7 2021

Publication series

Name	2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings

Conference

Conference	2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021
Country/Territory	United States
City	Virtual, Online
Period	12/5/21 → 12/7/21

Keywords

Agents
Generating
Generation through combination
Knowledge representation
Learning
Modeling

Access to Document

10.1109/SSCI50451.2021.9660045

Cite this

Doboli, A., & Doboli, S. (2021). A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination. In 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings (2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI50451.2021.9660045

Doboli, Alex ; Doboli, Simona. / A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination. 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings).

@inproceedings{c468a89fe05741aca3c4abddff5ed756,

title = "A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination",

abstract = "Many modern applications require both modeling and generative capabilities, so that they can produce novel outcomes that address requirements beyond the solutions used in model training. Current AI approaches arguably emphasize modeling but pay much less attention to generative capabilities. This paper presents a new learning and response generating (LRG) agent-based model, in which interacting agents continuously learn symbolic - numeric knowledge and create new outcomes (responses) using a set of five ways to combine concepts. Each way has both fast, reactive and a slow, planned versions. Experiments present the characteristics of an agent's modeling and generating capabilities.",

keywords = "Agents, Generating, Generation through combination, Knowledge representation, Learning, Modeling",

author = "Alex Doboli and Simona Doboli",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 ; Conference date: 05-12-2021 Through 07-12-2021",

year = "2021",

doi = "10.1109/SSCI50451.2021.9660045",

language = "English",

series = "2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings",

}

Doboli, A & Doboli, S 2021, A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination. in 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings. 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021, Virtual, Online, United States, 12/5/21. https://doi.org/10.1109/SSCI50451.2021.9660045

A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination. / Doboli, Alex; Doboli, Simona.
2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. (2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination

AU - Doboli, Alex

AU - Doboli, Simona

PY - 2021

Y1 - 2021

N2 - Many modern applications require both modeling and generative capabilities, so that they can produce novel outcomes that address requirements beyond the solutions used in model training. Current AI approaches arguably emphasize modeling but pay much less attention to generative capabilities. This paper presents a new learning and response generating (LRG) agent-based model, in which interacting agents continuously learn symbolic - numeric knowledge and create new outcomes (responses) using a set of five ways to combine concepts. Each way has both fast, reactive and a slow, planned versions. Experiments present the characteristics of an agent's modeling and generating capabilities.

AB - Many modern applications require both modeling and generative capabilities, so that they can produce novel outcomes that address requirements beyond the solutions used in model training. Current AI approaches arguably emphasize modeling but pay much less attention to generative capabilities. This paper presents a new learning and response generating (LRG) agent-based model, in which interacting agents continuously learn symbolic - numeric knowledge and create new outcomes (responses) using a set of five ways to combine concepts. Each way has both fast, reactive and a slow, planned versions. Experiments present the characteristics of an agent's modeling and generating capabilities.

KW - Agents

KW - Generating

KW - Generation through combination

KW - Knowledge representation

KW - Learning

KW - Modeling

UR - https://www.scopus.com/pages/publications/85125815601

U2 - 10.1109/SSCI50451.2021.9660045

DO - 10.1109/SSCI50451.2021.9660045

M3 - Conference contribution

T3 - 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings

BT - 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021

Y2 - 5 December 2021 through 7 December 2021

ER -

Doboli A, Doboli S. A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination. In 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. (2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings). doi: 10.1109/SSCI50451.2021.9660045

A Novel Learning and Response Generating Agent-based Model for Symbolic - Numeric Knowledge Modeling and Combination

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this