mlsanityData to 14 Oct 2026

Time series analysis with dynamic law exploration

arXiv 2104.10970 ↗First posted 22 Apr 2021cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper we examine, how the dynamic laws governing the time evolution of a time series can be identified. We give a finite difference equation as well as a differential equation representation for that. We also study, how the required symmetries, like time reversal can be imposed on the laws. We study the compression performance of linear laws on sound data.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 5 of its 10 references that are in the map. First posted on arXiv 22 Apr 2021.

Builds on

5 of 10 references.

References · 5

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  3. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  4. 2018Model-free, Model-based, and General Intelligencecited by 14
  5. 2020Understanding understanding: a renormalization group inspired model of (artificial) intelligencecited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 0; 2025: 1.

6 papers.

  1. 2022Reconstruction of observed mechanical motions with Artificial Intelligence toolscited by 7
  2. 2023LLT: An R package for Linear Law-based Feature Space Transformationcited by 3
  3. 2023Predicting the Price Movement of Cryptocurrencies Using Linear Law-based Transformationcited by 2
  4. 2023Learning ECG Signal Features Without Backpropagation Using Linear Lawscited by 2
  5. 2022Linear Laws of Markov Chains with an Application for Anomaly Detection in Bitcoin Pricescited by 1
  6. 2025ALT: A Python Package for Lightweight Feature Representation in Time Series Classificationcited by 0