مقایسهٔ روش‌ها

	طبقه‌بندی تصویر با شبکه‌های عصبی کانولوشنی (CNN)	TextCNN
حوزه	یادگیری عمیق	یادگیری عمیق
خانواده	Machine learning	Machine learning
سال پیدایش	2016	2014
پدیدآور	He, K. et al. (ResNet); Tan, M. & Le, Q.V. (EfficientNet)	Kim, Y.
نوع	Deep convolutional neural network (supervised)	Convolutional neural network (deep learning)
منبع بنیادین	He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR.	Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. EMNLP.
نام‌های دیگر	CNN — Görüntü Sınıflandırma (ResNet / VGG / EfficientNet), convolutional neural network image classifier, deep image classification, ResNet / VGG / EfficientNet	CNN — Metin Sınıflandırma (TextCNN), convolutional neural network for sentence classification, sentence-level CNN, TextCNN
مرتبط	5	5
خلاصه	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.	TextCNN is a convolutional neural network for text classification, introduced by Yoon Kim in 2014, that applies parallel convolution filters of different window sizes over word embeddings to capture local n-gram patterns. It is fast and effective for sentiment analysis and topic classification.