A highly scalable modular bottleneck neural network for image dimensionality reduction and image transformation

Carcenac, Manuel; Redif, Soydan

doi:10.1007/s10489-015-0715-5

Cited by 8 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, most dimensionality reduction algorithms deal with vector data, and some dimensionality reduction algorithms deal with high-order tensor data. The reason why the reduced dimension data representation is used is that the original high-dimensional space contains redundant information and noise information, which causes errors and reduces the accuracy in practical applications, such as image recognition [8]; by dimensionality reduction, we hope to reduce the error caused by redundant information and improve the accuracy of recognition.…”

Section: Related Workmentioning

confidence: 99%

Commodity Price Recognition and Simulation of Image Recognition Technology Based on the Nonlinear Dimensionality Reduction Method

Liu

Wang

Bai

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

Dimensionality reduction of images with high-dimensional nonlinear structure is the key to improving the recognition rate. Although some traditional algorithms have achieved some results in the process of dimensionality reduction, they also expose their respective defects. In order to achieve the ideal effect of high-dimensional nonlinear image recognition, based on the analysis of the traditional dimensionality reduction algorithm and refining its advantages, an image recognition technology based on the nonlinear dimensionality reduction method is proposed. As an effective nonlinear feature extraction method, the nonlinear dimensionality reduction method can find the nonlinear structure of datasets and maintain the intrinsic structure of data. Applying the nonlinear dimensionality reduction method to image recognition is to divide the input image into blocks, take it as a dataset in high-dimensional space, reduce the dimension of its structure, and obtain the low-dimensional expression vector of its eigenstructure so that the problem of image recognition can be carried out in a lower dimension. Thus, the computational complexity can be reduced, the recognition accuracy can be improved, and it is convenient for further processing such as image recognition and search. The defects of traditional algorithms are solved, and the commodity price recognition and simulation experiments are carried out, which verifies the feasibility of image recognition technology based on the nonlinear dimensionality reduction method in commodity price recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Commodity Price Recognition and Simulation of Image Recognition Technology Based on the Nonlinear Dimensionality Reduction Method

Liu

Wang

Bai

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

show abstract

“…Because of that, we are gradually faced during the convergence process with extremely large PMs and the computation of many iterations over high-dimensional data becomes subsequently intractable. For this reason, our previous work was limited either in polynomial parameters range (Carcenac and Redif 2016) or in number of iterations (Carcenac et al 2017).…”

Section: Introductionmentioning

confidence: 99%

Application of the sequential matrix diagonalization algorithm to high-dimensional functional MRI data

Carcenac¹,

Redif

2019

Comput Stat

Self Cite

View full text Add to dashboard Cite

This paper introduces an adaptation of the sequential matrix diagonalization (SMD) method to high-dimensional functional magnetic resonance imaging (fMRI) data. SMD is currently the most efficient statistical method to perform polynomial eigenvalue decomposition. Unfortunately, with current implementations based on dense polynomial matrices, the algorithmic complexity of SMD is intractable and it cannot be applied as such to high-dimensional problems. However, for certain applications, these polynomial matrices are mostly filled with null values and we have consequently developed an efficient implementation of SMD based on a GPU-parallel representation of sparse polynomial matrices. We then apply our "sparse SMD" to fMRI data, i.e. the temporal evolution of a large grid of voxels (as many as 29,328 voxels). Because of the energy compaction property of SMD, practically all the information is concentrated by SMD on the first polynomial principal component. Brain regions that are activated over time are thus reconstructed with great fidelity through analysis-synthesis based on the first principal component only, itself in the form of a sequence of polynomial parameters.

show abstract

Loss prediction of mountain flood disaster in villages and towns based on rough set RBF neural network

Hao

2021

Neural Comput & Applic

View full text Add to dashboard Cite

A highly scalable modular bottleneck neural network for image dimensionality reduction and image transformation

Cited by 8 publications

References 33 publications

Commodity Price Recognition and Simulation of Image Recognition Technology Based on the Nonlinear Dimensionality Reduction Method

Commodity Price Recognition and Simulation of Image Recognition Technology Based on the Nonlinear Dimensionality Reduction Method

Application of the sequential matrix diagonalization algorithm to high-dimensional functional MRI data

Loss prediction of mountain flood disaster in villages and towns based on rough set RBF neural network

Contact Info

Product

Resources

About