Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data
The self-organizing convolutional map (SOCOM) hybridizes convolutional neural networks, self-organizing maps, and gradient backpropagation optimization into a novel integrated unsupervised deep learning model. SOCOM structurally combines, architecturally stacks, and algorithmically fuses its deep/un...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/3/4/44 |
| _version_ | 1827671344645406720 |
|---|---|
| author | Christos Ferles Yannis Papanikolaou Stylianos P. Savaidis Stelios A. Mitilineos |
| author_facet | Christos Ferles Yannis Papanikolaou Stylianos P. Savaidis Stelios A. Mitilineos |
| author_sort | Christos Ferles |
| collection | DOAJ |
| description | The self-organizing convolutional map (SOCOM) hybridizes convolutional neural networks, self-organizing maps, and gradient backpropagation optimization into a novel integrated unsupervised deep learning model. SOCOM structurally combines, architecturally stacks, and algorithmically fuses its deep/unsupervised learning components. The higher-level representations produced by its underlying convolutional deep architecture are embedded in its topologically ordered neural map output. The ensuing unsupervised clustering and visualization operations reflect the model’s degree of synergy between its building blocks and synopsize its range of applications. Clustering results are reported on the STL-10 benchmark dataset coupled with the devised neural map visualizations. The series of conducted experiments utilize a deep VGG-based SOCOM model. |
| first_indexed | 2024-03-10T03:41:37Z |
| format | Article |
| id | doaj.art-02a243f6708a403e84f16e11aa3e3413 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-03-10T03:41:37Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-02a243f6708a403e84f16e11aa3e34132023-11-23T09:17:37ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902021-11-013487989910.3390/make3040044Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image DataChristos Ferles0Yannis Papanikolaou1Stylianos P. Savaidis2Stelios A. Mitilineos3Department of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, GreeceDepartment of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, GreeceDepartment of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, GreeceDepartment of Electrical and Electronics Engineering, University of West Attica, GR-12241 Aegaleo, Attica, GreeceThe self-organizing convolutional map (SOCOM) hybridizes convolutional neural networks, self-organizing maps, and gradient backpropagation optimization into a novel integrated unsupervised deep learning model. SOCOM structurally combines, architecturally stacks, and algorithmically fuses its deep/unsupervised learning components. The higher-level representations produced by its underlying convolutional deep architecture are embedded in its topologically ordered neural map output. The ensuing unsupervised clustering and visualization operations reflect the model’s degree of synergy between its building blocks and synopsize its range of applications. Clustering results are reported on the STL-10 benchmark dataset coupled with the devised neural map visualizations. The series of conducted experiments utilize a deep VGG-based SOCOM model.https://www.mdpi.com/2504-4990/3/4/44deep learningunsupervised learningconvolutional neural network (CNN)self-organizing map (SOM)clusteringvisualization |
| spellingShingle | Christos Ferles Yannis Papanikolaou Stylianos P. Savaidis Stelios A. Mitilineos Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data Machine Learning and Knowledge Extraction deep learning unsupervised learning convolutional neural network (CNN) self-organizing map (SOM) clustering visualization |
| title | Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data |
| title_full | Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data |
| title_fullStr | Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data |
| title_full_unstemmed | Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data |
| title_short | Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data |
| title_sort | deep self organizing map of convolutional layers for clustering and visualizing image data |
| topic | deep learning unsupervised learning convolutional neural network (CNN) self-organizing map (SOM) clustering visualization |
| url | https://www.mdpi.com/2504-4990/3/4/44 |
| work_keys_str_mv | AT christosferles deepselforganizingmapofconvolutionallayersforclusteringandvisualizingimagedata AT yannispapanikolaou deepselforganizingmapofconvolutionallayersforclusteringandvisualizingimagedata AT stylianospsavaidis deepselforganizingmapofconvolutionallayersforclusteringandvisualizingimagedata AT steliosamitilineos deepselforganizingmapofconvolutionallayersforclusteringandvisualizingimagedata |