পদ্ধতির তুলনা করুন

	সিএনএন চিত্র শ্রেণিবিভাগ	ডাইলেটেড সিএনএন
ক্ষেত্র	গভীর শিখন	গভীর শিখন
পরিবার	Machine learning	Machine learning
উদ্ভবের বছর	2016	2016
প্রবর্তক	He, K. et al. (ResNet); Tan, M. & Le, Q.V. (EfficientNet)	van den Oord, A. et al.; Bai, S., Kolter, J.Z. & Koltun, V.
ধরন	Deep convolutional neural network (supervised)	Deep learning (dilated 1D convolutional network)
মৌলিক উৎস	He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR.	van den Oord, A. et al. (2016). WaveNet: A Generative Model for Raw Audio. arXiv.
অপর নাম	CNN — Görüntü Sınıflandırma (ResNet / VGG / EfficientNet), convolutional neural network image classifier, deep image classification, ResNet / VGG / EfficientNet	Dilate Edilmiş CNN (WaveNet / TCN), WaveNet, Temporal Convolutional Network, TCN
সম্পর্কিত	5	5
সারসংক্ষেপ	CNN image classification uses deep convolutional architectures such as ResNet (He et al., 2016), VGG and EfficientNet (Tan & Le, 2019) to sort images into categories. Stacked convolutional layers learn a hierarchy of visual features directly from pixels, and skip (residual) connections prevent the vanishing-gradient problem in very deep networks.	A Dilated CNN is a one-dimensional convolutional network whose receptive field grows exponentially with depth, letting it model long-range structure in time series and audio signals. WaveNet (van den Oord et al., 2016) and the Temporal Convolutional Network of Bai, Kolter and Koltun (2018) are the prominent members of this family.