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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/12/2/235 |
| _version_ | 1797482178153545728 |
|---|---|
| author | Ruben Alvarez-Gonzalez Andres Mendez-Vazquez |
| author_facet | Ruben Alvarez-Gonzalez Andres Mendez-Vazquez |
| author_sort | Ruben Alvarez-Gonzalez |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-09T22:27:32Z |
| format | Article |
| id | doaj.art-f67e216978f148f58590db4df210e482 |
| institution | Directory Open Access Journal |
| issn | 2076-3425 |
| language | English |
| last_indexed | 2024-03-09T22:27:32Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj.art-f67e216978f148f58590db4df210e4822023-11-23T19:03:41ZengMDPI AGBrain Sciences2076-34252022-02-0112223510.3390/brainsci12020235Deep Learning Architecture Reduction for fMRI DataRuben Alvarez-Gonzalez0Andres Mendez-Vazquez1Department of Computer Science, Cinvestav Guadalajara, Zapopan 45015, MexicoDepartment of Computer Science, Cinvestav Guadalajara, Zapopan 45015, MexicoIn 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.https://www.mdpi.com/2076-3425/12/2/235CNNmachine learningdeep learningcomputer visiontransfer learning |
| spellingShingle | Ruben Alvarez-Gonzalez Andres Mendez-Vazquez Deep Learning Architecture Reduction for fMRI Data Brain Sciences CNN machine learning deep learning computer vision transfer learning |
| 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 | CNN machine learning deep learning computer vision transfer learning |
| url | https://www.mdpi.com/2076-3425/12/2/235 |
| work_keys_str_mv | AT rubenalvarezgonzalez deeplearningarchitecturereductionforfmridata AT andresmendezvazquez deeplearningarchitecturereductionforfmridata |