Distinct Feature Learning and Nonlinear Variation Pattern Discovery Using Regularized Autoencoders

Distinct Feature Learning and Nonlinear Variation Pattern Discovery Using Regularized Autoencoders

abstract: Feature learning and the discovery of nonlinear variation patterns in high-dimensional data is an important task in many problem domains, such as imaging, streaming data from sensors, and manufacturing. This dissertation presents several methods for learning and visualizing nonlinear varia...

Full description

Bibliographic Details
Other Authors: Howard, Phillip Ryan (Author)
Format: Doctoral Thesis
Language:English
Published: 2016
Subjects:
Industrial engineering
Artificial intelligence
Computer science
Autoassociative neural network
Autoencoder
Dimensionality reduction
Distinct features
Nonlinear principal component analysis
Nonlinear variation
Online Access:http://hdl.handle.net/2286/R.I.38620

Internet

http://hdl.handle.net/2286/R.I.38620

Similar Items