Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset

Samarth Srivastava; Suryabhan Yadav; Kalpaj Agrawalla; Tanisha Malhotra; N. V. Subba Reddy

doi:10.1109/ICRIEECE44171.2018.9009110

Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset

Samarth Srivastava, Suryabhan Yadav, Kalpaj Agrawalla, Tanisha Malhotra, N. V. Subba Reddy

Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose a neural network system of combined architecture, using a self-organizing map (SOM) along with the concept of backpropagation to recognize handwritten digits from the MNIST dataset. The handwritten digits of the MNIST dataset were processed through a computer vision pre-processor. The general problem with the backpropagation method, which is its big learning time for large datasets, is attempted to be removed when used with an unsupervised mode of classification such as SOM when the data being used for backpropagation is already made to go through the SOM algorithm.

Original language	English
Title of host publication	2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2080-2084
Number of pages	5
ISBN (Electronic)	9781538659946
DOIs	https://doi.org/10.1109/ICRIEECE44171.2018.9009110
Publication status	Published - 07-2018
Event	2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018 - Bhubaneswar, India Duration: 27-07-2018 → 28-07-2018

Publication series

Name	2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018

Conference

Conference	2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018
Country/Territory	India
City	Bhubaneswar
Period	27-07-18 → 28-07-18

All Science Journal Classification (ASJC) codes

Health Informatics
Computer Networks and Communications
Computer Science Applications
Hardware and Architecture
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Industrial and Manufacturing Engineering

Access to Document

10.1109/ICRIEECE44171.2018.9009110

Cite this

Srivastava, S., Yadav, S., Agrawalla, K., Malhotra, T., & Subba Reddy, N. V. (2018). Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset. In 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018 (pp. 2080-2084). [9009110] (2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRIEECE44171.2018.9009110

Srivastava, Samarth ; Yadav, Suryabhan ; Agrawalla, Kalpaj et al. / Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset. 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 2080-2084 (2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018).

@inproceedings{8633250b7a564fa4bd8e027b521f4ddb,

title = "Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset",

abstract = "In this paper, we propose a neural network system of combined architecture, using a self-organizing map (SOM) along with the concept of backpropagation to recognize handwritten digits from the MNIST dataset. The handwritten digits of the MNIST dataset were processed through a computer vision pre-processor. The general problem with the backpropagation method, which is its big learning time for large datasets, is attempted to be removed when used with an unsupervised mode of classification such as SOM when the data being used for backpropagation is already made to go through the SOM algorithm.",

author = "Samarth Srivastava and Suryabhan Yadav and Kalpaj Agrawalla and Tanisha Malhotra and {Subba Reddy}, {N. V.}",

year = "2018",

month = jul,

doi = "10.1109/ICRIEECE44171.2018.9009110",

language = "English",

series = "2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2080--2084",

booktitle = "2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018",

address = "United States",

note = "2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018 ; Conference date: 27-07-2018 Through 28-07-2018",

}

Srivastava, S, Yadav, S, Agrawalla, K, Malhotra, T & Subba Reddy, NV 2018, Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset. in 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018., 9009110, 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018, Institute of Electrical and Electronics Engineers Inc., pp. 2080-2084, 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018, Bhubaneswar, India, 27-07-18. https://doi.org/10.1109/ICRIEECE44171.2018.9009110

Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset. / Srivastava, Samarth; Yadav, Suryabhan; Agrawalla, Kalpaj et al.

2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 2080-2084 9009110 (2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset

AU - Srivastava, Samarth

AU - Yadav, Suryabhan

AU - Agrawalla, Kalpaj

AU - Malhotra, Tanisha

AU - Subba Reddy, N. V.

PY - 2018/7

Y1 - 2018/7

N2 - In this paper, we propose a neural network system of combined architecture, using a self-organizing map (SOM) along with the concept of backpropagation to recognize handwritten digits from the MNIST dataset. The handwritten digits of the MNIST dataset were processed through a computer vision pre-processor. The general problem with the backpropagation method, which is its big learning time for large datasets, is attempted to be removed when used with an unsupervised mode of classification such as SOM when the data being used for backpropagation is already made to go through the SOM algorithm.

AB - In this paper, we propose a neural network system of combined architecture, using a self-organizing map (SOM) along with the concept of backpropagation to recognize handwritten digits from the MNIST dataset. The handwritten digits of the MNIST dataset were processed through a computer vision pre-processor. The general problem with the backpropagation method, which is its big learning time for large datasets, is attempted to be removed when used with an unsupervised mode of classification such as SOM when the data being used for backpropagation is already made to go through the SOM algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85081961548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85081961548&partnerID=8YFLogxK

U2 - 10.1109/ICRIEECE44171.2018.9009110

DO - 10.1109/ICRIEECE44171.2018.9009110

M3 - Conference contribution

T3 - 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018

SP - 2080

EP - 2084

BT - 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018

Y2 - 27 July 2018 through 28 July 2018

ER -

Srivastava S, Yadav S, Agrawalla K, Malhotra T, Subba Reddy NV. Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset. In 2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 2080-2084. 9009110. (2018 International Conference on Recent Innovations in Electrical, Electronics and Communication Engineering, ICRIEECE 2018). doi: 10.1109/ICRIEECE44171.2018.9009110

Recognition of Handwritten Digits Using Computer Vision Preprocessor Based Combined Architecture of Self-Organizing Map and Backpropagation on MNIST Dataset

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this