CUDA-enabled implementation of a neural network algorithm for handwritten digit recognition

Izotov, P. Yu.; Kazanskiy, Nikolay L.; Golovashkin, D. L.; Суханов, Сергей Васильевич

doi:10.3103/s1060992x11020032

Cited by 7 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Developed methods, devices and technologies allowed not only to solve a wide range of problems of creation and research of focusators, but also to start designing effective machine vision systems [109][110][111][112] , investigating unique properties of diffractive nanophotonics components [113][114][115][116][117][118][119][120] and also to proceed to development of new high-efficiency technological processes.…”

Section: Resultsmentioning

confidence: 99%

Technological applications of focusing optical elements

Абульханов

2015

SPIE Proceedings

View full text Add to dashboard Cite

The article analyzes a wide range of technologies generated by the application of focusators of laser radiation. I give a brief review of the methods of monitoring substrate and forming a diffraction microrelief, optical systems and devices for experimental research of focusators, laser technologies and units on their basis. In particular, I analyze using focusator into the ring for growing single-crystalline fibers in device of mini pedestal, using focusator into a set of rings for information-measuring system of three-dimensional control of grid spacers and other applications of focusators.Keywords: focusators of laser radiation, diffractive optical elements, formation of diffractive microrelief, laser technologies, information-measuring system, single-crystal fibers, centering of optical devices and machine parts.

show abstract

Section: Resultsmentioning

confidence: 99%

Technological applications of focusing optical elements

Абульханов

2015

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…For this reason, for colorization, it is necessary to use not only data about the color of the point, but also additional information. The source of such information can serve as another image (reference image), or expert opinion, or, identified in the image by a neural network an additional high-level features [7][8][9][10].…”

Section: Analysis Of Image Processing Algorithms Based On Neural Netwmentioning

confidence: 99%

Convolutional neural network in the images colorization problem

Bulygin¹,

Gayanova²,

Vulfin

et al. 2019

Proceedings of the v International Conference Information Technology and Nanotechnology 2019

View full text Add to dashboard Cite

Object of the research are modern structures and architectures of neural networks for image processing. Goal of the work is improving the existing image processing algorithms based on the extraction and compression of features using neural networks using the colorization of black and white images as an example. The subject of the work is the algorithms of neural network image processing using heterogeneous convolutional networks in the colorization problem. The analysis of image processing algorithms with the help of neural networks is carried out, the structure of the neural network processing system for image colorization is developed, colorization algorithms are developed and implemented. To analyze the proposed algorithms, a computational experiment was conducted and conclusions were drawn about the advantages and disadvantages of each of the algorithms.

show abstract

“…Solving a similar problem, Izotov et al [7], used an ANN-based algorithm to recognize handwritten digits, using a CUDA-based implementation. The training time improvements were about 6 times less than an algorithm executed on CPU, and on instance classification there were reductions of about 9 times in execution time.…”

Section: Related Workmentioning

confidence: 99%

Facial Recognition Using Neural Networks over GPGPU

Balarini

Nesmachnow²,

Rodriguez³

2012

CLEIej

View full text Add to dashboard Cite

This article introduces a parallel neural network approach implemented over Graphic Processing Units (GPU) to solve a facial recognition problem, which consists in deciding where the face of a person in a certain image is pointing. The proposed method uses the parallel capabilities of GPU in order to train and evaluate a neural network used to solve the abovementioned problem. The experimental evaluation demonstrates that a significant reduction on computing times can be obtained allowing solving large instances in reasonable time. Speedup greater than 8 is achieved when contrasted with a sequential implementation and classification rate superior to 85 % is also obtained.

show abstract

CUDA-enabled implementation of a neural network algorithm for handwritten digit recognition

Cited by 7 publications

References 2 publications

Technological applications of focusing optical elements

Technological applications of focusing optical elements

Convolutional neural network in the images colorization problem

Facial Recognition Using Neural Networks over GPGPU

Contact Info

Product

Resources

About