English

Autoencoder with Ordered Variance for Nonlinear Model Identification

Systems and Control 2024-02-23 v1 Machine Learning Systems and Control

Abstract

This paper presents a novel autoencoder with ordered variance (AEO) in which the loss function is modified with a variance regularization term to enforce order in the latent space. Further, the autoencoder is modified using ResNets, which results in a ResNet AEO (RAEO). The paper also illustrates the effectiveness of AEO and RAEO in extracting nonlinear relationships among input variables in an unsupervised setting.

Keywords

Cite

@article{arxiv.2402.14031,
  title  = {Autoencoder with Ordered Variance for Nonlinear Model Identification},
  author = {Midhun T. Augustine and Parag Patil and Mani Bhushan and Sharad Bhartiya},
  journal= {arXiv preprint arXiv:2402.14031},
  year   = {2024}
}

Comments

14 pages, 8 figures

R2 v1 2026-06-28T14:56:06.696Z