Reducing the Dimensionality of Data with Neural Networks

Author:

Hinton G. E.1,Salakhutdinov R. R.1

Affiliation:

1. Department of Computer Science, University of Toronto, 6 King's College Road, Toronto, Ontario M5S 3G4, Canada.

Abstract

High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such “autoencoder” networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.

Publisher

American Association for the Advancement of Science (AAAS)

Subject

Multidisciplinary

Reference17 articles.

1. Learning sets of filters using back-propagation

2. D. DeMers, G. Cottrell, Advances in Neural Information Processing Systems 5 (Morgan Kaufmann, San Mateo, CA, 1993), pp. 580–587.

3. Replicator Neural Networks for Universal Optimal Source Coding

4. Dimension Reduction by Local Principal Component Analysis

5. P. Smolensky, Parallel Distributed Processing: Volume 1: Foundations, D. E. Rumelhart, J. L. McClelland, Eds. (MIT Press, Cambridge, 1986), pp. 194–281.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3