A Comparative Study on Neural Network Architectures for Image Recognition Applications
Keywords:
Neural Networks, Image Recognition, CNNs, ResNets, Vision Transformers.Abstract
Several neural network architectures are investigated and tested, including traditional LeNet-style Convolutional NeuralNetworks (CNNs), multi-layer perceptron’s, and state-of-the-art (SoTA) architectures like ResNet, DenseNet, and VisionTransformers (ViTs). Deep learning has transformed the landscape of computer vision, making the correct model selection critical while building high performance applications
References
LeCun, Y., et al. "Gradient-based learning applied to document recognition." Proceedings of the IEEE, 1998.
Hinton, G. E., et al. "Improving neural networks by preventing co-adaptation of feature detectors." arXiv preprint arXiv:1207.0580, 2012.
Downloads
Published
2023-01-20
How to Cite
Rahul Reddy Bandhela, RamMohan Reddy Kundavaram. (2023). A Comparative Study on Neural Network Architectures for Image Recognition Applications . Journal of Computational Analysis and Applications (JoCAAA), 31(1), 1334–1342. Retrieved from https://www.eudoxuspress.com/index.php/pub/article/view/3566
Issue
Section
Articles
