2、Autoencoder in Autoencoder Networks 在本节中,我们将介绍AE2-Network,用于学习具有一组多视图样本 X=X(1),..,X(V) 的完整表示,其中 X(V)∈Rdv×n 是第v个视图的特征矩阵,其中V,n和 dv 分别是第V个视图的视图数量,样本数量和特征空间的维数。 2.1 方法简介 AE2-Nets(如图1所示)的关键目标
Adversarial Autoencoder https://arxiv.org/abs/1511.05644 A generative models is to yield new data which subjects to a certain distribution so as to capture the distribution. An adversarial autoencoder...Autoencoder review Autoencoder Reducing the Dimensionality of Data with Neural Networks, Science...
Differently, in this paper, we focus on unsupervised representation learning and propose a novel framework termed Autoencoder in Autoencoder Networks (AE2-Nets), which integrates information from heterogeneous sources into an intact representation by the nested autoencoder framework. The proposed method ...
本文提出了一种新的框架AE2-Nets，专注于无监督表示学习。AE2-Nets通过嵌套的自动编码器框架，将来自不同来源的信息集成到一个完整的表示中，以解决当前多视图学习中相关性和独立性之间的平衡问题。该方法在统一框架内联合执行视图特定的表示学习和多视图信息编码，灵活平衡多个视图之间的互补性和一致性。AE...
AE2-Nets: Autoencoder in Autoencoder Networks Changqing Zhang1∗, Yeqing Liu1∗, Huazhu Fu2 1College of Intelligence and Computing, Tianjin University, Tianjin, China 2Inception Institute of Artificial Intelligence, Abu Dhabi, UAE {zhangchangqing; yeqing}@tju.edu.cn; hzfu@ieee.org Abstract ...