OPTIMIZED CONVOLUTIONAL NEURAL NETWORK ARCHITECTURE FOR IMAGE RECOGNITION BASED ON ARTIFICIAL INTELLIGENCE.
Keywords:
artificial intelligence, deep learning, convolutional neural networks (CNN), image processing, optimization, feature extraction.Abstract
This article proposes a convolutional neural network (CNN) architecture
optimized for automatic image processing and feature extraction using artificial
intelligence (AI) and deep learning technologies. During the research, existing CNN
models such as ResNet, DenseNet, and EfficientNet were analyzed to identify their
strengths and weaknesses. Based on these findings, optimization strategies were
developed by adjusting the number of layers and kernel sizes, selecting pooling layers
and activation functions, and applying transfer learning and quantization methods to
improve computational efficiency.
References
1. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition.
CVPR,
2016.
2. Huang G., Liu Z., Van Der Maaten L., Weinberger K. Densely Connected
Convolutional
Networks.
CVPR,
2017.
3. Tan M., Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural
Networks.
ICML,
2019.
4. Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016.
5. Shorten C., Khoshgoftaar T.M. A Survey on Image Data Augmentation for Deep
Learning. Journal of Big Data, 2019.
6. Rustamov M. Use of modern methods in teaching “information technology” in
medical education. Science and Innovation, 2023.
7.
Rustamov M. Enhance students' knowledge and skills with multimedia tools in
an innovative educational environment. Science and Innovation, 2023.
