 |
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
|
Issue: February 2026
Volume 11 | Issue 2
Review Result and Publication of Paper within : 2-3 days
Click Here For more DetailsFor Authors
Forms / Download
Published Issue Details
Editorial Board
Other IMP Links
Facts & Figure
Impact Factor : 8.14
Issue per Year : 12
Volume Published : 11
Issue Published : 117
Article Submitted : 21318
Article Published : 8476
Total Authors : 22301
Total Reviewer : 802
Total Countries : 156
Indexing Partner
Licence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
Published Paper Details
|
|
| Paper Title: | Evaluation of Classification Results for Convolutional Neural Network Architectures on the MNIST and CIFAR-10 Datasets Using TensorFlow |
| Authors Name: | Denny Nur Ramadhan , Prof. Dr. Eng. Cahya Rahmad, ST., M.Kom. , Yan Watequlis Syaifudin, ST., M.MT., Ph.D. |
| Download E-Certificate: | Download |
| Author Reg. ID: |
IJRTI_208829
|
| Published Paper Id: | IJRTI2512143 |
| Published In: | Volume 10 Issue 12, December-2025 |
| DOI: | |
| Abstract: | Abstract— This study evaluates 40 convolutional neural network (CNN) architectures from TensorFlow on MNIST and CIFAR-10 datasets representing different visual complexities. Under unified experimental conditions, models from ConvNeXt, EfficientNet, ResNet, DenseNet, MobileNet, and other families were assessed for accuracy, loss, weighted metrics, training time, and memory usage. Results show distinct architectural effectiveness: on MNIST, most models achieved near-saturation performance (24 exceeding 98% accuracy) with minimal dispersion, indicating lightweight architectures suffice for simple tasks. On CIFAR-10, performance varied substantially (67.21–96.28% accuracy), with modern, capacity-rich architectures like ConvNeXtXLarge excelling but requiring greater computational resources. Comparative analysis reveals dataset-dependent optimality—EfficientNetV2 dominates MNIST while ConvNeXt excels on CIFAR-10—and demonstrates that architectural complexity yields meaningful returns only on visually complex datasets. These findings provide a practical framework for model selection based on task complexity and resource constraints. |
| Keywords: | Convolutional Neural Networks, Image Classification, MNIST, CIFAR-10, TensorFlow, Deep Learning Benchmark. |
| Cite Article: | "Evaluation of Classification Results for Convolutional Neural Network Architectures on the MNIST and CIFAR-10 Datasets Using TensorFlow", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 12, page no.b347-b354, December-2025, Available :http://www.ijrti.org/papers/IJRTI2512143.pdf |
| Downloads: | 000225 |
| ISSN: |
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016 An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator |
| Publication Details: |
Published Paper ID: IJRTI2512143
Registration ID:208829
Published In: Volume 10 Issue 12, December-2025
DOI (Digital Object Identifier):
Page No: b347-b354 Country: Kab. Malang, East Java, Indonesia Research Area: Computer Science & Technology Publisher : IJ Publication Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2512143 Published Paper PDF: https://www.ijrti.org/papers/IJRTI2512143 |
| Share Article: | |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijrti.org
| Google Scholar | ResearcherID Thomson Reuters | Mendeley : reference manager | Academia.edu |
| arXiv.org : cornell university library | Research Gate | CiteSeerX | DOAJ : Directory of Open Access Journals |
| DRJI | Index Copernicus International | Scribd | DocStoc |
ISSN Details
 |
 |
|
ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED,
Journal Starting Year (ESTD) : 2016
DOI (A digital object identifier)
| Providing A digital object identifier by DOI.ONE How to Get DOI? |
Conference
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Important Details
Join RMS/Earn 300
WhatsApp
Click Here
Click Here
Indexing Partner |
|||
| Copyright © 2026 - All Rights Reserved - IJRTI | |||