A Convolutional Deep Self-Organizing Map Feature extraction for machine learning

Sakkari, Mohamed; Zaied, Mourad

doi:10.1007/s11042-020-08822-9

Cited by 15 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The set of all possible SQL queries must be divided into an unknown number of clusters. For this purpose, the device of Kohonen's Self-Organizing Maps (hereinafter SOM) is used [15,16,17]. The SOM training algorithm is developed, based on the use of a rational value of the winning neuron topological neighborhood width, which makes it possible to configure the neural network to prevent its overfitting.…”

Section: Methodsmentioning

confidence: 99%

Development of Intelligent Tools for Detecting Resource-intensive Database Queries

Alghazali¹,

Polshchykov²,

Hailan³

et al. 2021

IJACSA

View full text Add to dashboard Cite

The detection of resource-intensive queries which consume an excessive amount of time, processor, disk, and memory resources is one of the most popular vulnerabilities of Database Management Systems (DBMS). The tools for monitoring and optimizing queries typically used in modern DBMS were analyzed, and their shortcomings were identified. Subsequently, the relevance of new intelligent tools' development for timely and reliable detection of resource-intensive queries to databases was distinctly justified. The study concluded a set of analysis of an extended statistical parameter which indicated to be of interest for identifying resource-intensive queries. The initial set of queries' parameters reduced by two consecutive methods. Firstly, normalizing the set of indicators using a sigmoid function. Secondly, selecting a finite number of principal components based on the Cattell test. Whereas the clustering of a set of queries performed using self-organizing Kohonen maps. Suggestions for further studies in the classification algorithm context were indicated in lights of the study's conclusions.

show abstract

Section: Methodsmentioning

confidence: 99%

Development of Intelligent Tools for Detecting Resource-intensive Database Queries

Alghazali¹,

Polshchykov²,

Hailan³

et al. 2021

IJACSA

View full text Add to dashboard Cite

show abstract

“…However, they trained several self-organizing maps for each input subspace and used SOM for data visualization only. In another work, Sakkari and Zaied [20] proposed an architecture which alternate self-organizing, RELU rectification function, and abstraction layer. In their work, the self-organizing layer is composed of a multiple region-based SOMs with each map focuses on modeling a local sub-region of the input image.…”

Section: Related Workmentioning

confidence: 99%

“…It is clear that, using 3D-SOM grid for DCSOM-2 features and 4D-SOM grid for DCSOM-1 features outperform state-of-the-art results in MNIST-rand and MNIST-img datasets, respectively. These 1.2 Deep belief network + linear SVM [41] 1.9 CDBN [42] 0.82 ConvNet [40] 0.53 DCTNet [34] 0.74 ScatNet-2 [12] 0.43 PCANet-2 [11] 0.66 LDANet-2 [11] 0.62 DSOM [23] 3.83 UDSOM [20] 1.06 CSOM (2D) [14] 0.81 SOMNet [13] 0.86 CR-MSOM [15] 0.97 DCSOM-1 (4D) 0.78 DCSOM-2 (4D) 0.57 results prove that features of DCSOM are more robust to noise than other methods when we carefully choose the appropriate dimension of SOM grid. The hard quantization of the SOM mapping highly improve the representation of the noisy patches as compared to other CNN architecture which use either supervised or unsupervised learning.…”

Section: B Experiments Using Mnist Variations Datasetsmentioning

confidence: 99%

“…A lot of research works have been developed to exploit the advantages of self-organizing map learning in deep architectures such as: Convolutional Recursive Modified Self-Organizing Map (CR-MSOM) [15], Convolutional Self-organing map (CSOM) [16], self-organizing maps with convolutional layers [17], Denoising Autoencoder Self-Organizing Map (DASOM) [18], Unsupervised Deep Self-Organizing Map (UDSOM) [19], [20], Deep Product Self-Organizing Maps (DP-SOM) [21], [22]. However, our proposed Deep Convolutional Self-Organizing Map (DCSOM) model is completely different from the previously mentioned deep SOM architectures.…”

Section: Introductionmentioning

confidence: 99%

“…All previous architectures utilized 2-dimensional SOM grid while none of them explored the impact of increasing the dimensionality of SOM grid. The UDSOM architecture proposed in [19], [20] utilized multiple SOMs to learn region-specific features. However, our proposed model trains only one convolutional SOM layer in each stage as contrary to other methods [20], [23], [24] which also trains multiple region-specific SOMs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Convolutional Self-Organizing Map Network for Robust Handwritten Digit Recognition

Aly

Almotairi

2020

IEEE Access

View full text Add to dashboard Cite

Deep Convolutional Neural Networks (DCNN) are currently the predominant technique commonly used to learn visual features from images. However, the complex structure of most recent DCNNs impose two major requirements namely, huge labeled dataset and high computational resources. In this paper, we develop a new efficient deep unsupervised network to learn invariant image representation from unlabeled visual data. The proposed Deep Convolutional Self-organizing Maps (DCSOM) network comprises a cascade of convolutional SOM layers trained sequentially to represent multiple levels of features. The 2D SOM grid is commonly used for either data visualization or feature extraction. However, this work employs high dimensional map size to create a new deep network. The N-Dimensional SOM (ND-SOM) grid is trained to extract abstract visual features using its classical competitive learning algorithm. The topological order of the features learned from ND-SOM helps to absorb local transformation and deformation variations exhibited in the visual data. The input image is divided into an overlapped local patches where each local patch is represented by the N-coordinates of the winner neuron in the ND-SOM grid. Each dimension of the ND-SOM can be considered as a non-linear principal component and hence it can be exploited to represent the input image using N-Feature Index Image (FII) bank. Multiple convolutional SOM layers can be cascaded to create a deep network structure. The output layer of the DCSOM network computes local histograms of each FII bank in the final convolutional SOM layer. A set of experiments using MNIST handwritten digit database and all its variants are conducted to evaluate the robust representation of the proposed DCSOM network. Experimental results reveal that the performance of DCSOM outperforms state-of-the-art methods for noisy digits and achieve a comparable performance with other complex deep learning architecture for other image variations.

show abstract

Feature Extraction-Based Deep Self-Organizing Map

Sakkari

Hamdi

Elmannai

et al. 2022

Circuits Syst Signal Process

View full text Add to dashboard Cite

A Convolutional Deep Self-Organizing Map Feature extraction for machine learning

Cited by 15 publications

References 33 publications

Development of Intelligent Tools for Detecting Resource-intensive Database Queries

Development of Intelligent Tools for Detecting Resource-intensive Database Queries

Deep Convolutional Self-Organizing Map Network for Robust Handwritten Digit Recognition

Feature Extraction-Based Deep Self-Organizing Map

Contact Info

Product

Resources

About