Year: 2023
Type: book-chapter
Abstract: The convolutional neural networks (CNNs) are widely used for image classification tasks because CNNs can successfully capture spatial hierarchies and patterns in images.A dataset can be utilized to evaluate the performance of various types of CNNs.To compare the effectiveness of four CNN models for image classification on specific datasets, this study utilizes the MNIST dataset to train four classic CNNs and subsequently compares and evaluates the classification outcomes.The four models are LeNet (LeNet), AlexNet, Visual Geometry Group Network (VGGNet) and Visual Geometry Group Network (ResNet).In order to address the performance of four neural network models in image classification, a controlled experiment is conducted.The results of this study indicate LeNet is the most suitable model on the MNIST dataset.While the other three models also exhibit commendable classification results, they fall short of the overall performance achieved by the LeNet model.The other three models can be used with challenging datasets.
Author: Ziling Luo
Institution: Xiamen University Malaysia
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4388999264
