Cargando…

Deep Learning Architecture Reduction for fMRI Data

In recent years, deep learning models have demonstrated an inherently better ability to tackle non-linear classification tasks, due to advances in deep learning architectures. However, much remains to be achieved, especially in designing deep convolutional neural network (CNN) configurations. The nu...

Descripción completa

Detalles Bibliográficos
Autores principales: Alvarez-Gonzalez, Ruben, Mendez-Vazquez, Andres
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8870362/
https://www.ncbi.nlm.nih.gov/pubmed/35203997
http://dx.doi.org/10.3390/brainsci12020235
_version_ 1784656724585611264
author Alvarez-Gonzalez, Ruben
Mendez-Vazquez, Andres
author_facet Alvarez-Gonzalez, Ruben
Mendez-Vazquez, Andres
author_sort Alvarez-Gonzalez, Ruben
collection PubMed
description In recent years, deep learning models have demonstrated an inherently better ability to tackle non-linear classification tasks, due to advances in deep learning architectures. However, much remains to be achieved, especially in designing deep convolutional neural network (CNN) configurations. The number of hyper-parameters that need to be optimized to achieve accuracy in classification problems increases with every layer used, and the selection of kernels in each CNN layer has an impact on the overall CNN performance in the training stage, as well as in the classification process. When a popular classifier fails to perform acceptably in practical applications, it may be due to deficiencies in the algorithm and data processing. Thus, understanding the feature extraction process provides insights to help optimize pre-trained architectures, better generalize the models, and obtain the context of each layer’s features. In this work, we aim to improve feature extraction through the use of a texture amortization map (TAM). An algorithm was developed to obtain characteristics from the filters amortizing the filter’s effect depending on the texture of the neighboring pixels. From the initial algorithm, a novel geometric classification score (GCS) was developed, in order to obtain a measure that indicates the effect of one class on another in a classification problem, in terms of the complexity of the learnability in every layer of the deep learning architecture. For this, we assume that all the data transformations in the inner layers still belong to a Euclidean space. In this scenario, we can evaluate which layers provide the best transformations in a CNN, allowing us to reduce the weights of the deep learning architecture using the geometric hypothesis.
format Online
Article
Text
id pubmed-8870362
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88703622022-02-25 Deep Learning Architecture Reduction for fMRI Data Alvarez-Gonzalez, Ruben Mendez-Vazquez, Andres Brain Sci Article In recent years, deep learning models have demonstrated an inherently better ability to tackle non-linear classification tasks, due to advances in deep learning architectures. However, much remains to be achieved, especially in designing deep convolutional neural network (CNN) configurations. The number of hyper-parameters that need to be optimized to achieve accuracy in classification problems increases with every layer used, and the selection of kernels in each CNN layer has an impact on the overall CNN performance in the training stage, as well as in the classification process. When a popular classifier fails to perform acceptably in practical applications, it may be due to deficiencies in the algorithm and data processing. Thus, understanding the feature extraction process provides insights to help optimize pre-trained architectures, better generalize the models, and obtain the context of each layer’s features. In this work, we aim to improve feature extraction through the use of a texture amortization map (TAM). An algorithm was developed to obtain characteristics from the filters amortizing the filter’s effect depending on the texture of the neighboring pixels. From the initial algorithm, a novel geometric classification score (GCS) was developed, in order to obtain a measure that indicates the effect of one class on another in a classification problem, in terms of the complexity of the learnability in every layer of the deep learning architecture. For this, we assume that all the data transformations in the inner layers still belong to a Euclidean space. In this scenario, we can evaluate which layers provide the best transformations in a CNN, allowing us to reduce the weights of the deep learning architecture using the geometric hypothesis. MDPI 2022-02-08 /pmc/articles/PMC8870362/ /pubmed/35203997 http://dx.doi.org/10.3390/brainsci12020235 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Alvarez-Gonzalez, Ruben
Mendez-Vazquez, Andres
Deep Learning Architecture Reduction for fMRI Data
title Deep Learning Architecture Reduction for fMRI Data
title_full Deep Learning Architecture Reduction for fMRI Data
title_fullStr Deep Learning Architecture Reduction for fMRI Data
title_full_unstemmed Deep Learning Architecture Reduction for fMRI Data
title_short Deep Learning Architecture Reduction for fMRI Data
title_sort deep learning architecture reduction for fmri data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8870362/
https://www.ncbi.nlm.nih.gov/pubmed/35203997
http://dx.doi.org/10.3390/brainsci12020235
work_keys_str_mv AT alvarezgonzalezruben deeplearningarchitecturereductionforfmridata
AT mendezvazquezandres deeplearningarchitecturereductionforfmridata