مقاله رمزگذارهای خودکار خنثی سازی کانولوشن انباشته برای نمایش ویژگی

عنوان مقاله فارسی: رمزگذارهای خودکار خنثی سازی کانولوشن انباشته برای نمایش ویژگی عنوان مقاله لاتین: Stacked Convolutional Denoising Auto-Encoders for Feature Representation نویسندگان: Bo Du; Wei Xiong; Jia Wu; Lefei Zhang; Liangpei Zhang; Dacheng Tao تعداد صفحات: 10 سال انتشار: 2017 زبان: لاتین Abstract: Deep networks have achieved excellent performance in learning representation from visual data. However, the supervised deep models like convolutional neural network require large quantities of labeled data, which are very expensive to obtain. To solve this problem, this paper proposes an unsupervised deep network, called the stacked convolutional denoising auto-encoders, which can map images to hierarchical representations without any label information. The network, optimized by layer-wise training, is