CONVOLUTIONAL NEURAL NETWORKS: FUNDAMENTALS AND WORKING PRINCIPLES
Keywords:
Convolutional Neural Network, CNN, artificial intelligence, deep learning, image processing, convolution, pooling, feature extractionAbstract
This article analyzes the theoretical foundations, structure, and working principles of Convolutional Neural Networks (CNNs). The importance of CNN models in image processing, their differences from traditional neural networks, and their role in modern artificial intelligence systems are discussed. In addition, the functions of key components such as convolution, pooling, and fully connected layers are scientifically explained. The results of the study demonstrate the effectiveness and wide applicability of CNN technology.
References
1. Boué L. Deep Learning for Pedestrians: Backpropagation in CNNs. - 2018.
2. Shin H. C., Roth H. R., Gao M. et al. Deep Convolutional Neural Networks for Computer-Aided Detection. - 2016.
3. Chatfield K., Simonyan K., Vedaldi A., Zisserman A. Delving Deep into Convolutional Nets. - 2014.
4. Бишоп К. Распознавание образов и машинное обучение. - М.: Вильямс, 2006.
5. Goodfellow I., Bengio Y., Courville A. Deep Learning. - Cambridge: MIT Press, 2016.
