Please use this identifier to cite or link to this item:
Title: Autonomous CNN (AutoCNN): a data-driven approach to network architecture determination
Authors: Aradhya, Abhay M S
Ashfahani, Andri
Angelina, Fienny
Pratama, Mahardhika
de Mello, Rodrigo Fernandes
Sundaram, Suresh
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: Aradhya, A. M. S., Ashfahani, A., Angelina, F., Pratama, M., de Mello, R. F. & Sundaram, S. (2022). Autonomous CNN (AutoCNN): a data-driven approach to network architecture determination. Information Sciences, 607, 638-653.
Project: RG90/20
Journal: Information Sciences
Abstract: Designing a Convolutional Neural Networks (CNN) is a complex task and requires expert knowledge to optimize the performance and network architecture. In this paper, a novel data-driven approach is proposed to determine the architecture of CNN models. The proposed Autonomous Convolutional Neural Networks (AutoCNNThe executable code and original numerical results can be downloaded from ( algorithm introduces data driven strategies for addition of new convolutional layers, pruning of redundant filters and training cycle optimization. AutoCNN is evaluated using MNIST, MNIST-rot-back-image, Fashion MNIST and the ADHD200 datasets to measure the performance on small datasets with varied feature distributions. The results indicate that AutoCNN optimizes the CNN network architecture and helps maximise the classification performance. The data-driven network determination approach introduced in this paper was found to not only provides competitive performance similar to existing evolutionary computation based network determination algorithms in literature, but was found to be an effective optimization tool to improve the performance of existing CNN architectures. Further, the AutoCNN was found to highly immune to noise in the dataset and has proven to be effective method to transfer knowledge between related datasets. Therefore, the AutoCNN is a highly versatile CNN architecture determination tool that has a wide range of applications in the field of autonomous driving, medical image analysis, image enhancement, camera based security monitoring and image based fault detection.
ISSN: 0020-0255
DOI: 10.1016/j.ins.2022.05.100
Schools: School of Computer Science and Engineering 
Rights: © 2022 Elsevier Inc. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 50

Updated on Feb 23, 2024

Web of ScienceTM
Citations 50

Updated on Oct 31, 2023

Page view(s)

Updated on Feb 29, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.