首页> 外文会议>International Conference on Artificial Neural Networks >PCI: Principal Component Initialization for Deep Autoencoders
【24h】

PCI: Principal Component Initialization for Deep Autoencoders

机译:PCI:深度自动编码器的主要组件初始化

获取原文

摘要

An autoencoder (AE) is one of the important neural network methods for dimensionality reduction problems. Unfortunately, however, deep AEs have the drawback in trainability which often makes obtaining a good performance a difficult task owing to their model complexity. This paper proposes a simple weight initialization algorithm called the principal component initialization (PCI) method to improve and stabilize the generalization performance of deep AEs in one shot. PCI uses orthogonal bases of the original data space obtained with principal component analysis and transposed ones as initial weights of the AEs. The proposed method significantly outperforms the current de facto standard initialization method for image reconstruction tasks.
机译:自动编码器(AE)是解决降维问题的重要神经网络方法之一。但是,不幸的是,深层AE具有可训练性的缺点,由于其模型复杂性,通常使获得良好的性能成为一项艰巨的任务。本文提出了一种简单的权重初始化算法,称为主成分初始化(PCI)方法,以提高并稳定一次深层AE的泛化性能。 PCI使用通过主成分分析获得的原始数据空间的正交基和转置的基作为AE的初始权重。所提出的方法明显胜过当前用于图像重建任务的事实上的标准初始化方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号