Advancing broad learning through structured feature generation

© 2025 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

Detalles Bibliográficos
Autores: Mallea Ruz, Mario Carlos|||0009-0005-8295-088X, Nebot Castells, M. Àngela|||0000-0002-4621-8262, Múgica Álvarez, Francisco|||0000-0003-2843-0427
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/446788
Acceso en línea:https://hdl.handle.net/2117/446788
https://dx.doi.org/10.1016/j.eswa.2025.129948
Access Level:acceso abierto
Palabra clave:Broad learning system
Randomized neural networks
Random features
Feature generation
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_e6eb6fc2eb0933394c8b3a28c8e96661
oai_identifier_str oai:upcommons.upc.edu:2117/446788
network_acronym_str ES
network_name_str España
repository_id_str
spelling Advancing broad learning through structured feature generationMallea Ruz, Mario Carlos|||0009-0005-8295-088XNebot Castells, M. Àngela|||0000-0002-4621-8262Múgica Álvarez, Francisco|||0000-0003-2843-0427Broad learning systemRandomized neural networksRandom featuresFeature generationÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial© 2025 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).Deep neural networks achieve strong performance in big data scenarios, while requiring extensive iterative parameter optimization, making them inefficient and suboptimal in scarce data scenarios. Broad Learning System (BLS) has gained popularity as an efficient, effective, and incremental learning model. BLS relies on independent and identically distributed random feature generation. Although efficient, the literature has shown that this approach can lead to suboptimal and redundant representations. This paper introduces Structured BLS (SBLS), a novel reinterpretation of BLS components. SBLS enhances latent features by incorporating a structured random basis, which provides a beneficial inductive bias that promotes neuronal specialization to learn specific patterns in the data while reducing the redundancy issue of the classic BLS. Experimental results in various classification and regression datasets demonstrate that SBLS outperforms BLS in terms of performance, robustness to noise, and interpretability, while remaining efficient and easy to deploy. Our findings emphasize the need for focused feature generation through random weights in neural networks and reservoir computing. In fact, we are transitioning from a chaotic to a controlled exploration of patterns. Moreover, we illustrate how our approach can incorporate task-specific knowledge into neuron behavior by design. SBLS has practical implications for real-world applications that involve data scarcity. By refining the way randomness is exploited in neural networks, our work challenges the conventional wisdom that improved performance requires deeper architectures or complex optimization strategies. Instead, we show that intelligent feature generation can unlock significant gains at minimal additional cost.Supported by the ‘Siemens Energy AI Chair: Energy Sustainability for a Decarbonized Society 5.0’ (TSI-100930-2023-5), funded by the Secretary of State for Digitalization and Artificial Intelligence through the ENIA 2022 Chairs call, and co-funded by the European Union-Next Generation EU.Peer Reviewed13 - Acció per al ClimaElsevier20252025-10-0820252025-11-21journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/446788https://dx.doi.org/10.1016/j.eswa.2025.129948reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4467882026-05-27T15:37:01Z
dc.title.none.fl_str_mv Advancing broad learning through structured feature generation
title Advancing broad learning through structured feature generation
spellingShingle Advancing broad learning through structured feature generation
Mallea Ruz, Mario Carlos|||0009-0005-8295-088X
Broad learning system
Randomized neural networks
Random features
Feature generation
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short Advancing broad learning through structured feature generation
title_full Advancing broad learning through structured feature generation
title_fullStr Advancing broad learning through structured feature generation
title_full_unstemmed Advancing broad learning through structured feature generation
title_sort Advancing broad learning through structured feature generation
dc.creator.none.fl_str_mv Mallea Ruz, Mario Carlos|||0009-0005-8295-088X
Nebot Castells, M. Àngela|||0000-0002-4621-8262
Múgica Álvarez, Francisco|||0000-0003-2843-0427
author Mallea Ruz, Mario Carlos|||0009-0005-8295-088X
author_facet Mallea Ruz, Mario Carlos|||0009-0005-8295-088X
Nebot Castells, M. Àngela|||0000-0002-4621-8262
Múgica Álvarez, Francisco|||0000-0003-2843-0427
author_role author
author2 Nebot Castells, M. Àngela|||0000-0002-4621-8262
Múgica Álvarez, Francisco|||0000-0003-2843-0427
author2_role author
author
dc.subject.none.fl_str_mv Broad learning system
Randomized neural networks
Random features
Feature generation
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Broad learning system
Randomized neural networks
Random features
Feature generation
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description © 2025 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-10-08
2025
2025-11-21
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/446788
https://dx.doi.org/10.1016/j.eswa.2025.129948
url https://hdl.handle.net/2117/446788
https://dx.doi.org/10.1016/j.eswa.2025.129948
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422809200984065
score 15,811543

Similares en LA Referencia