Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network

Frezza-Buet, Hervé

doi:10.1016/j.neucom.2007.12.024

Cited by 43 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work [35] demonstrates the validity of this model to represent objects in images with its own structure and its capacity to preserve the input space topology. A new version of the GNG model called GNG-Seq has been created to manage image sequences under time constraints by taking advantage the GNG structure representation, obtained in previous frames, and by considering that at video frequency the slight motion of the mobile agents present in the frames can be modeled.…”

Section: Neural Architecture To Represent and Track Objectsmentioning

confidence: 88%

“…For the search, we used the parallel reduction technique described in [35]. This technique accelerates operations such as the search for the minimum value in parallel in large data sets.…”

Section: Parallel Reductionmentioning

confidence: 99%

“…In particular, there are several works that use the self-organizing models for the representation and tracking of objects. Fritzke [33] proposed a variation of the original growing neural gas (GNG) model [34] to map nonstationary distributions that Frezza-Buet [35] apply to the representation and tracking of people. In [36], amendments to self-organizing models for the characterization of the movement are proposed.…”

Section: Introductionmentioning

confidence: 99%

“…In [36], amendments to self-organizing models for the characterization of the movement are proposed. From the works cited, only Frezza-Buet [35] represent both local and global motions. However, there is no consideration of time constraints, and the algorithm does not exploit the knowledge acquired in previous frames for the purpose of segmentation or prediction.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Real time motion estimation using a neural architecture implemented on GPUs

García-Rodríguez

Orts-Escolano

Angelopoulou

et al. 2014

J Real-Time Image Proc

View full text Add to dashboard Cite

This work describes a neural network based architecture that represents and estimates object motion in videos. This architecture addresses multiple computer vision tasks such as image segmentation, object representation or characterization, motion analysis and tracking. The use of a neural network architecture allows for the simultaneous estimation of global and local motion and the representation of deformable objects. This architecture also avoids the problem of finding corresponding features while tracking moving objects. Due to the parallel nature of neural networks, the architecture has been implemented on GPUs that allows the system to meet a set of requirements such as: time constraints management, robustness, high processing speed and re-configurability. Experiments are presented that demonstrate the validity of our architecture to solve problems of mobile agents tracking and motion analysis.

show abstract

Section: Neural Architecture To Represent and Track Objectsmentioning

confidence: 88%

“…For the search, we used the parallel reduction technique described in [35]. This technique accelerates operations such as the search for the minimum value in parallel in large data sets.…”

Section: Parallel Reductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Real time motion estimation using a neural architecture implemented on GPUs

García-Rodríguez

Orts-Escolano

Angelopoulou

et al. 2014

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…There exist several variants of GNG for non-stationary environments such as FrezzaBuet (2014), Fritzke (1997) and Frezza-Buet (2008). Perhaps the most known variant is GNG-U (Fritzke 1997) which is proposed by the original authors of GNG.…”

mentioning

confidence: 99%

An adaptive algorithm for anomaly and novelty detection in evolving data streams

Bouguelia

Nowaczyk

Payberah

2018

Data Min Knowl Disc

View full text Add to dashboard Cite

In the era of big data, considerable research focus is being put on designing efficient algorithms capable of learning and extracting high-level knowledge from ubiquitous data streams in an online fashion. While, most existing algorithms assume that data samples are drawn from a stationary distribution, several complex environments deal with data streams that are subject to change over time. Taking this aspect into consideration is an important step towards building truly aware and intelligent systems. In this paper, we propose GNG-A, an adaptive method for incremental unsupervised learning from evolving data streams experiencing various types of change. The proposed method maintains a continuously updated network (graph) of neurons by extending the Growing Neural Gas algorithm with three complementary mechanisms, allowing it to closely track both gradual and sudden changes in the data distribution. First, an adaptation mechanism handles local changes where the distribution is only non-stationary in some regions of the feature space. Second, an adaptive forgetting mechanism identifies and removes neurons that become irrelevant due to the evolving nature of the stream. Finally, a probabilistic evolution mechanism creates new neurons when there is a need to represent data in new regions of the feature space. The proposed method is demonstrated for anomaly and novelty detection in non-stationary environments. Results show that the method handles different data distributions and efficiently reacts to various types of change.

show abstract

Clustering II: Topics in Clustering

Swamy²

2013

Neural Networks and Statistical Learning

View full text Add to dashboard Cite

Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network

Cited by 43 publications

References 18 publications

Real time motion estimation using a neural architecture implemented on GPUs

Real time motion estimation using a neural architecture implemented on GPUs

An adaptive algorithm for anomaly and novelty detection in evolving data streams

Clustering II: Topics in Clustering

Contact Info

Product

Resources

About