mlsanityData to 14 Oct 2026

Using Autoencoders and AutoDiff to Reconstruct Missing Variables in a Set of Time Series

arXiv 2308.10496 ↗First posted 21 Aug 2023cs.LG cs.AI stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing black box modeling approaches in machine learning suffer from a fixed input and output feature combination. In this paper, a new approach to reconstruct missing variables in a set of time series is presented. An autoencoder is trained as usual with every feature on both sides and the neural network parameters are fixed after this training. Then, the searched variables are defined as missing variables at the autoencoder input and optimized via automatic differentiation. This optimization is performed with respect to the available features loss calculation. With this method, different input and output feature combinations of the trained model can be realized by defining the searched variables as missing variables and reconstructing them. The combination can be changed without training the autoencoder again. The approach is evaluated on the base of a strongly nonlinear electrical component. It is working well for one of four variables missing and generally even for multiple missing variables.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 35 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

13 of 35 references.

References · 13

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2019An Introduction to Variational Autoencoderscited by 1,000
  3. 2015Automatic differentiation in machine learning: a surveycited by 855
  4. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  5. 2015Unsupervised Learning of Video Representations using LSTMscited by 435
  6. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 242
  7. 2021An Introduction to Deep Generative Modelingcited by 104
  8. 2016Auxiliary Deep Generative Modelscited by 72
  9. 2020Solving inverse problems using conditional invertible neural networkscited by 37
  10. 2020Time Series Data Imputation: A Survey on Deep Learning Approachescited by 34
  11. 2022Universal approximation property of invertible neural networkscited by 30
  12. 2018Relational Autoencoder for Feature Extractioncited by 23
1 more
  1. 2019Fast Transient Simulation of High-Speed Channels Using Recurrent Neural Networkcited by 2

Built on by

Not cited yet.