Výsledky vyhľadávania - Nonnegativity-constrained autoencoder

  • Zobrazené výsledky 1 - 8 z 8
Upresniť hľadanie
  1. 1

    Driver identification based on hidden feature extraction by using adaptive nonnegativity-constrained autoencoder Autor Chen, Jie, Wu, ZhongCheng, Zhang, Jun

    ISSN: 1568-4946, 1872-9681
    Vydavateľské údaje: Elsevier B.V 01.01.2019
    Vydané v Applied soft computing (01.01.2019)
    “… identification accuracy and long prediction time. We first propose using an unsupervised three-layer nonnegativity-constrained autoencoder to adaptive search the optimal size of the sliding window, then construct a deep nonnegativity-constrained…”
    Získať plný text
    Journal Article
  2. 2

    Driving Safety Risk Prediction Using Cost-Sensitive With Nonnegativity-Constrained Autoencoders Based on Imbalanced Naturalistic Driving Data Autor Chen, Jie, Wu, ZhongCheng, Zhang, Jun

    ISSN: 1524-9050, 1558-0016
    Vydavateľské údaje: New York IEEE 01.12.2019
    “… In this paper, we propose a novel cost-sensitive L 1 /L 2 -nonnegativity-constrained deep autoencoder network for driving safety risk prediction…”
    Získať plný text
    Journal Article
  3. 3

    Learning a referenceless stereopair quality engine with deep nonnegativity constrained sparse autoencoder Autor Jiang, Qiuping, Shao, Feng, Lin, Weisi, Jiang, Gangyi

    ISSN: 0031-3203, 1873-5142
    Vydavateľské údaje: Elsevier Ltd 01.04.2018
    Vydané v Pattern recognition (01.04.2018)
    “…) images based on deep nonnegativity constrained sparse autoencoder (DNCSAE). To address the quality issue of stereopairs whose perceived quality is not only…”
    Získať plný text
    Journal Article
  4. 4

    Milling tool condition monitoring for difficult-to-cut materials based on NCAE and IGWO-SVM Autor Wang, Siqi, Yan, Shichao, Sun, Yuwen

    ISSN: 0268-3768, 1433-3015
    Vydavateľské údaje: London Springer London 01.11.2023
    “… To handle this issue, this paper proposed a novel method for monitoring tool wear conditions based on the nonnegativity-constrained autoencoder (NCAE…”
    Získať plný text
    Journal Article
  5. 5

    Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data Autor Ayinde, Babajide O, Zurada, Jacek M

    ISSN: 2331-8422
    Vydavateľské údaje: Ithaca Cornell University Library, arXiv.org 25.12.2018
    Vydané v arXiv.org (25.12.2018)
    “… This is especially prominent when multilayer deep learning architectures are used. This paper demonstrates how to remove these bottlenecks within the architecture of Nonnegativity Constrained Autoencoder (NCSAE…”
    Získať plný text
    Paper
  6. 6

    Deep Learning of Part-Based Representation of Data Using Sparse Autoencoders With Nonnegativity Constraints Autor Hosseini-Asl, Ehsan, Zurada, Jacek M., Nasraoui, Olfa

    ISSN: 2162-237X, 2162-2388, 2162-2388
    Vydavateľské údaje: United States IEEE 01.12.2016
    “… (nonnegativity-constrained autoencoder), that learns features that show part-based representation of data…”
    Získať plný text
    Journal Article
  7. 7

    Cross-covariance regularized autoencoders for nonredundant sparse feature representation Autor Chen, Jie, Wu, ZhongCheng, Zhang, Jun, Li, Fang, Li, WenJing, Wu, ZiHeng

    ISSN: 0925-2312, 1872-8286
    Vydavateľské údaje: Elsevier B.V 17.11.2018
    Vydané v Neurocomputing (Amsterdam) (17.11.2018)
    “… Existing feature representation algorithms based on the sparse autoencoder and nonnegativity-constrained autoencoder tend to produce duplicative encoding and decoding receptive fields, which leads…”
    Získať plný text
    Journal Article
  8. 8

    Nonredundant sparse feature extraction using autoencoders with receptive fields clustering Autor Ayinde, Babajide O., Zurada, Jacek M.

    ISSN: 0893-6080, 1879-2782, 1879-2782
    Vydavateľské údaje: United States Elsevier Ltd 01.09.2017
    Vydané v Neural networks (01.09.2017)
    “… Existing autoencoder-based data representation techniques tend to produce a number of encoding and decoding receptive fields of layered autoencoders that are duplicative, thereby leading…”
    Získať plný text
    Journal Article