• Home
  • Search
  • Evolving Convolutional Neural Networks for Image and Text Classification Tasks
  • https://doi.org/10.26686/wgtn.27897288Copy DOI Icon

Evolving Convolutional Neural Networks for Image and Text Classification Tasks

  • Nov 24, 2024
  • Trevor Londt
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

<p dir="ltr">In the Machine Learning field, Convolutional Neural Networks (CNNs) have successfully been applied to image and text classification tasks. Innovative research in CNN design, such as the usage of deeper models and data augmentation, has resulted in significantly increased performance. However, the resultant growth in CNN complexity from these innovations has required a corresponding increase in expert skills to design them. Furthermore, CNN architectures and data augmentation techniques designed for a classification task in one domain may not generalise to other classification tasks in a different domain, meaning the difficult and costly design process must be repeated. Evolutionary Deep Learning Neural Architecture Search (EDLNAS) has been used to automatically evolve performant CNNs for various classification tasks, including image and text classification. However, the approach suffers from high computation costs, often resulting in algorithms needing to focus on a single task for a single domain, thereby missing the opportunity to achieve algorithm generalisability. This thesis aims to investigate and improve upon the efficiency, effectiveness, and generalisability of EDLNAS of CNNs for image and text classification tasks without using data augmentation. Achieving this goal can mitigate three significant problems: the high-computational cost of EDLNAS algorithms, the generalisability problem, and the problem of collecting additional training data or implementing bespoke data augmentation techniques that require costly expert domain knowledge. This thesis proposes a new, configurable, and extensible version of Cellular Encoding (CE), including supporting network structures designed to represent and construct novel CNN architectures. The encoding successfully represents various novel CNN architectures of varying width and depth, suitable for image or text classification tasks. This thesis proposes a data augmentation-free EDLNAS method to automatically evolve novel CNN architectures for image and text classification tasks, using the proposed CE representation and predesigned state-of-the-art micro-architectures. The results show that peer-competitive CNNs can be evolved in less than one GPU day across image or text domains. Next, this thesis proposes to evolve micro-architectures to boost the performance in evolving CNN architectures for image and text classification tasks without data augmentation. The results show that this is achieved without increasing the number of GPU days required. This thesis proposes the first data augmentation-free cooperative coevolution algorithm to decompose a CNN architecture into four constituent sub-architectures, each evolved separately but in cooperation, to synthesise performant CNN architectures. A new population structure and novelty injection mechanism are proposed to create a better balance between exploration and exploitation. Furthermore, a persistent offline database is created, storing tens of thousands of evolved CNN architectures and associated performance metrics. The results show that highly competitive CNN architectures can be evolved in less than one GPU day, with the algorithm achieving a good balance between exploration and exploitation during the evolution process. Finally, this thesis proposes the first EDLNAS method that models a database of stored CNN architectures and performance metrics to create a deep neural network prediction model to predict the potential classification accuracy of a candidate CNN architecture, thereby removing the need to conduct back-propagation training during the evolutionary process. The method is able to evolve a large population of CNN architectures for both image and text classification tasks in seconds, making the evolutionary process near real-time while still achieving state-of-the-art peer-competitive results.</p>

Similar Papers
  • Supplementary Content

Texture Patterns for Object Recognition and Content-Based Color Image Retrieval

  • Dec 21, 2020
  • Griffith Research Online (Griffith University, Queensland, Australia)
  • Muhammad Asif
  • Conference Article
  • Citations7

Automatic Design of Convolutional Neural Networks using Grammatical Evolution

  • Oct 01, 2019
  • Ricardo H.R Lima +2
  • Research Article
  • Citations885

Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification.

  • Apr 21, 2020
  • IEEE Transactions on Cybernetics
  • Yanan Sun +4
  • Conference Article
  • Citations1

Prediction of Oral Cancer Using Deep Transfer Learning

  • Apr 02, 2024
  • Bolaji A Omodunbi +5
  • Conference Article
  • Citations1

Fully automatic CNN design with inception blocks

  • Jun 30, 2021
  • Togzhan Barakbayeva +1
  • Research Article
  • Citations3

A Structurally Regularized CNN Architecture via Adaptive Subband Decomposition.

  • Jan 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Pavel Sinha +2
  • PDF
  • Research Article
  • Citations10

Classification Analysis of Back propagation-Optimized CNN Performance in Image Processing

  • Mar 31, 2023
  • Journal of Systems Engineering and Information Technology (JOSEIT)
  • Putrama Alkhairi +1
  • Research Article
  • Citations4

Human Activity Recognition in a Realistic and Multiview Environment Based on Two-Dimensional Convolutional Neural Network

  • May 09, 2023
  • Journal of Artificial Intelligence and Technology
  • Ashish Khare +2
  • Conference Article
  • Citations1

Evolving Optimal Convolutional Neural Networks

  • Dec 01, 2020
  • Subhashis Banerjee +1
  • Research Article
  • Citations30

Hyper-sinh: An accurate and reliable function from shallow to deep learning in TensorFlow and Keras

  • Jul 19, 2021
  • Machine Learning with Applications
  • Luca Parisi +3
  • Research Article
  • Citations50

Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks

  • Jan 01, 2021
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • Khaled Koutini +2
  • Research Article

Comparison of transfer-learning for lightweight pre-trained model on image classification

  • Mar 28, 2024
  • Applied and Computational Engineering
  • Wenhan Zheng
  • Research Article
  • Citations7

A novel study for automatic two-class COVID-19 diagnosis (between COVID-19 and Healthy, Pneumonia) on X-ray images using texture analysis and 2-D/3-D convolutional neural networks

  • Jan 29, 2022
  • Multimedia Systems
  • Huseyin Ya\U015Far +1
  • Research Article

A Comparative Study of CNN Architectures for Food Image Classification with Data Augmentation and Zero-Shot Analysis

  • Oct 14, 2025
  • International Journal of Science and Engineering Applications
  • Research Article
  • Citations14

A convolutional fuzzy min-max neural network

  • May 17, 2020
  • Neurocomputing
  • Trupti R Chavan +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.