A New Self-Organizing Neural Gas Model based on Bregman Divergences

Palomo, Esteban J.; Molina‐Cabello, Miguel A.; López‐Rubio, Ezequiel; Luque‐Baena, Rafael Marcos

doi:10.1109/ijcnn.2018.8489545

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work is based on the Growing Hierarchical Bregman Neural Gas (GHBNG) network [16], which can be regarded as a Growing Hierarchical Neural Gas (GHNG) model [15] where Bregman divergences are employed to calculate the winning unit. Let φ : S → R be a function with real values and strictly convex, which is defined on a convex set S ⊆ R D , where D is the input data dimension [3,4,19].…”

Section: The Ghbng Modelmentioning

confidence: 99%

“…Therefore, the most suitable divergence can be specified according to the input data by using Bregman divergences. In this paper, a self-organizing neural network called the Growing Hierarchical Bregman Neural Gas (GHBNG) [16] is used for CQ, which is a variation of the GHNG model which considers Bregman divergences as an extension of the classic Euclidean distance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Color Quantization with a Neural Gas Model Based on Bregman Divergences

Palomo

Benito-Picazo

Domínguez

et al. 2021

16th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2021)

Self Cite

View full text Add to dashboard Cite

In this paper, a new color quantization method based on a self-organized artificial neural network called the Growing Hierarchical Bregman Neural Gas (GHBNG) is proposed. This neural network is based on Bregman divergences, from which the squared Euclidean distance is a particular case. Thus, the best suitable Bregman divergence for color quantization can be selected according to the input data. Moreover, the GHBNG yields a tree-structured model that represents the input data so that a hierarchical color quantization can be obtained, where each layer of the hierarchy contains a different color quantization of the original image. Experimental results confirm the color quantization capabilities of this approach.

show abstract

Section: The Ghbng Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hierarchical Color Quantization with a Neural Gas Model Based on Bregman Divergences

Palomo

Benito-Picazo

Domínguez

et al. 2021

16th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2021)

Self Cite

View full text Add to dashboard Cite

show abstract

“…CollAR is based on the Growing When Required (GWR) neural network [12,13], which takes inspiration from self-organizing map (SOM) [14,15], their extension self-organizing neural network (SOINN) [16,17] and growing neural gas (GNG) [18][19][20]. Differently from solutions based on neural networks with a fixed architecture (i.e., where the number of layers and neurons is defined before training and it does not change), GWR is an incremental neural network that is capable of automatically and dynamically adapting its architecture.…”

Section: Introductionmentioning

confidence: 99%

Collaborative activity recognition with heterogeneous activity sets and privacy preferences

Civitarese

Zampatti

et al. 2021

AIS

View full text Add to dashboard Cite

One of the major challenges in Human Activity Recognition (HAR) based on machine learning is the scarcity of labeled data. Indeed, collecting a sufficient amount of training data to build a reliable recognition problem is often prohibitive. Among the many solutions in the literature to mitigate this issue, collaborative learning is emerging as a promising direction to distribute the annotation burden over multiple users that cooperate to build a shared recognition model. One of the major issues of existing methods is that they assume a static activity model with a fixed set of target activities. In this paper, we propose a novel approach that is based on Growing When Required (GWR) neural networks. A GWR network continuously adapts itself according to the input training data, and hence it is particularly suited when the users share heterogeneous sets of activities. Like in federated learning, for the sake of privacy preservation, each user contributes to the global activity classifier by sharing personal model parameters, and not by directly sharing data. In order to further mitigate privacy threats, we implement a strategy to avoid releasing model parameters that may indirectly reveal information about activities that the user specifically marked as private. Our results on two well-known publicly available datasets show the effectiveness and the flexibility of our approach.

show abstract

A convolutional autoencoder and a neural gas model based on Bregman divergences for hierarchical color quantization

et al. 2023

View full text Add to dashboard Cite

A New Self-Organizing Neural Gas Model based on Bregman Divergences

Cited by 4 publications

References 19 publications

Hierarchical Color Quantization with a Neural Gas Model Based on Bregman Divergences

Hierarchical Color Quantization with a Neural Gas Model Based on Bregman Divergences

Collaborative activity recognition with heterogeneous activity sets and privacy preferences

A convolutional autoencoder and a neural gas model based on Bregman divergences for hierarchical color quantization

Contact Info

Product

Resources

About