Identifying nonlinear variation patterns with deep autoencoders

Phillip Howard, Daniel W. Apley, George Runger

    Research output: Contribution to journalArticlepeer-review


    The discovery of nonlinear variation patterns in high-dimensional profile data is an important task in many quality control and manufacturing settings. We present an automated method for discovering nonlinear variation patterns using deep autoencoders. The approach provides a functional mapping from a low-dimensional representation to the original spatially-dense feature space of the profile data that is both interpretable and efficient with respect to preserving information. We compare our deep autoencoder approach to several other methods for discovering variation patterns in profile data. Our results indicate that deep autoencoders consistently outperform the alternative approaches in reproducing the original profiles from the learned variation sources.

    Original languageEnglish (US)
    Pages (from-to)1089-1103
    Number of pages15
    JournalIISE Transactions
    Issue number12
    StatePublished - Dec 2 2018


    • autoassociative neural network
    • autoencoder
    • deep learning
    • Profile data
    • variation pattern
    • visualization

    ASJC Scopus subject areas

    • Industrial and Manufacturing Engineering

    Fingerprint Dive into the research topics of 'Identifying nonlinear variation patterns with deep autoencoders'. Together they form a unique fingerprint.

    Cite this