Pasar al contenido principal

APRENDIZAJE PROFUNDO EXPLICABLE EN EL ANALISIS DE IMAGENES MEDICAS: NUEVAS METODOLOGIAS, ESTRATEGIAS DE EVALUACION Y APLICACIONES CLINICAS

PID2023-146261OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Neural network pruning using nonlinear oblique subspace projections

  • Pena-Campos, Johan
  • Caicedo Dorado, Alexander
  • Patiño Guevara, Diego
  • Ocampo-Martínez, Carlos|||0000-0001-9251-6044
© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The increasing complexity of deep neural networks often leads to overparameterization, limiting their deployment in resource-constrained environments. This paper introduces a novel pruning methodology based on Nonlinear Oblique Subspace Projections (NObSP), an algorithm originally developed to enhance the interpretability of kernel regression models. In this work, NObSP is extended to neural networks to estimate the contribution of individual neurons and entire layers to the network's output. This is achieved by quantifying the nonlinear transformations performed by the network on its inputs and internal representations. By computing the magnitude of these variables, neurons contributing minimally to the network's output are identified. Specifically, neurons with a nonlinear effect magnitude falling below a defined threshold are pruned, effectively removing them from the network. Consequently, NObSP provides a data-driven, interpretability-based approach to neural network pruning, leading to simplified and efficient models with minor performance impact. This method offers a clear framework for understanding which components of a neural network are critical for its function, facilitating the development of more compact and interpretable deep learning models. Finally, the efficacy of NObSP for pruning is demonstrated in CIFAR-10 and MNIST classification problems, where it is compared to traditional pruning algorithms based on the Ln norm., The work of this paper is supported by the following funds: the Condonable Credit Doctoral Support Grant from the Academic Vice Rector’s Office, the Scholarship Loan Program Grant from Colfuturo, the Spanish project SEAMLESS: Sustainable learning-based Management of Multiresource Large-scale Systems (ref. PID2023-148840OBI00), funded by MCIN/AEI/10.13039/501100011033/FEDER, UE and the project PID2023-146261OB-I00, funded by Ministry of Science and Innovation of Spain., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Neural network pruning using nonlinear oblique subspace projections

  • Pena-Campos, Johan
  • Caicedo Dorado, Alexander
  • Patiño Guevara, Diego
  • Ocampo-Martínez, Carlos
© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., The increasing complexity of deep neural networks often leads to overparameterization, limiting their deployment in resource-constrained environments. This paper introduces a novel pruning methodology based on Nonlinear Oblique Subspace Projections (NObSP), an algorithm originally developed to enhance the interpretability of kernel regression models. In this work, NObSP is extended to neural networks to estimate the contribution of individual neurons and entire layers to the network's output. This is achieved by quantifying the nonlinear transformations performed by the network on its inputs and internal representations. By computing the magnitude of these variables, neurons contributing minimally to the network's output are identified. Specifically, neurons with a nonlinear effect magnitude falling below a defined threshold are pruned, effectively removing them from the network. Consequently, NObSP provides a data-driven, interpretability-based approach to neural network pruning, leading to simplified and efficient models with minor performance impact. This method offers a clear framework for understanding which components of a neural network are critical for its function, facilitating the development of more compact and interpretable deep learning models. Finally, the efficacy of NObSP for pruning is demonstrated in CIFAR-10 and MNIST classification problems, where it is compared to traditional pruning algorithms based on the Ln norm., The work of this paper is supported by the following funds: the Condonable Credit Doctoral Support Grant from the Academic Vice Rector’s Office, the Scholarship Loan Program Grant from Colfuturo, the Spanish project SEAMLESS: Sustainable learning-based Management of Multiresource Large-scale Systems (ref. PID2023-148840OBI00), funded by MCIN/AEI/10.13039/501100011033/FEDER, UE and the project PID2023-146261OB-I00, funded by Ministry of Science and Innovation of Spain., Peer Reviewed, Postprint (author's final draft)