作者:
Pei, YanUniv Aizu
Div Comp Sci Fukushima Ku Aizu Wakamatsu Fukushima 9658580 Japan
We propose a method that uses kernelmethod-based algorithms to implement an autoencoder. deeplearning-based algorithms have two characteristics, one is the high level data abstraction, the other is the multiple leve...
详细信息
ISBN:
(纸本)9781538616451
We propose a method that uses kernelmethod-based algorithms to implement an autoencoder. deeplearning-based algorithms have two characteristics, one is the high level data abstraction, the other is the multiple level data transformations and representations. The kernelmethod is one of the approaches that can be used in linear and non-linear transformations. It should be one of the implementations of these transformations in the deeplearning. In this paper, the encoder part and decoder part of the autoencoder are implemented by kernel-based principal component analysis and kernel-based linear regression, respectively. As autoencoder is a basic structure and algorithm in deeplearning, the proposed method can implement deeplearning model and algorithm using duplicate structures. We use image data to evaluate our proposed method. The results show that kernel-based autoencoder can represent and restore image data, but the performance depends on the kernel function and its parameters' selection. We also discuss and analyse some open topics and works towards a study of kernel method-based deep learning.
暂无评论