Evolutionary Optimization-Based Training of Convolutional Neural Networks for OCR Applications

被引：0

作者：

Fedorovici, Lucian-Ovidiu ^{[1
]}

Precup, Radu-Emil ^{[1
]}

Dragan, Florin ^{[1
]}

Purcaru, Constantin ^{[1
]}

机构：

[1] Politehn Univ Timisoara, Dept Automat & Appl Informat, Timisoara, Romania

来源：

2013 17TH INTERNATIONAL CONFERENCE ON SYSTEM THEORY, CONTROL AND COMPUTING (ICSTCC) | 2013年

关键词：

back-propagation; convolutional neural netrorks; Gravitational Search Algorithms; Particle Swarm Optimization; SEARCH; DESIGN; ALGORITHMS; PSO;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents aspects concerning the implementation of two training algorithms for convolutional neural networks (CNNs) used in optical character recognition (OCR) applications. The two training algorithms involve evolutionary optimization algorithms represented by a Gravitational Search Algorithm (GSA) and a Particle Swarm Optimization (PSO) Algorithm. New CNN training algorithms are offered on the basis of using GSA and PSO algorithms in combination with back-propagation in order to encourage performance improvements by avoiding local minima. A comparison between the new training algorithms is carried out focusing on the analysis of convergence, computational cost and accuracy in the framework of a benchmark problem specific to OCR applications.

引用

页码：207 / 212

页数：6

共 50 条

[1] OPTIMIZATION-BASED NEURAL NETWORKS COMPRESSION
Tahiri, Younes
Seddik, Mohamed El Amine
Tamaazousti, Mohamed
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 3512 - 3516
[2] Bayesian Optimization-Based Global Optimal Rank Selection for Compression of Convolutional Neural Networks
Kim, Taehyeon
Lee, Jieun
Choe, Yoonsik
[J]. IEEE ACCESS, 2020, 8 : 17605 - 17618
[3] Designing convolutional neural networks with constrained evolutionary piecemeal training
Sapra, Dolly
Pimentel, Andy D.
[J]. APPLIED INTELLIGENCE, 2022, 52 (15) : 17103 - 17117
[4] Designing convolutional neural networks with constrained evolutionary piecemeal training
Dolly Sapra
Andy D. Pimentel
[J]. Applied Intelligence, 2022, 52 : 17103 - 17117
[5] SOCIAL-SPIDER OPTIMIZATION-BASED ARTIFICIAL NEURAL NETWORKS TRAINING AND ITS APPLICATIONS FOR PARKINSON'S DISEASE IDENTIFICATION
Pereira, L. A. M.
Rodrigues, D.
Ribeiro, P. B.
Papa, J. P.
Weber, Silke A. T.
[J]. 2014 IEEE 27TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 2014, : 14 - 17
[6] Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks
Zhou, Chaowei
Xiong, Aimin
[J]. SENSORS, 2023, 23 (04)
[7] Optimization-based convolutional neural model for the classification of white blood cells
Devi, Tulasi Gayatri
Patil, Nagamma
[J]. JOURNAL OF BIG DATA, 2024, 11 (01)
[8] Evolutionary optimization of convolutional neural networks for cancer miRNA biomarkers classification
Lopez-Rincon, Alejandro
Tonda, Alberto
Elati, Mohamed
Schwander, Olivier
Piwowarski, Benjamin
Gallinari, Patrick
[J]. APPLIED SOFT COMPUTING, 2018, 65 : 91 - 100
[9] Applications and Comparisons of Optimization Algorithms Used in Convolutional Neural Networks
Seyyarer, Ebubekir
Uckan, Taner
Hark, Cengiz
Ayata, Faruk
Inan, Mevlut
Karci, Ali
[J]. 2019 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA PROCESSING (IDAP 2019), 2019,
[10] OCR with a Convolutional Neural Networks Integration Model in Machine Vision
Zhang, Rui
Wu, Xiaojun
Qiu, Lingteng
Yang, Zhicheng
[J]. TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018), 2018, 10806

← 1 2 3 4 5 →