Summary of An Unsupervised Approach For Periodic Source Detection in Time Series, by Berken Utku Demirel and Christian Holz
An Unsupervised Approach for Periodic Source Detection in Time Series
by Berken Utku Demirel, Christian Holz
First submitted to arxiv on: 1 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers propose a novel method for detecting periodic patterns in noisy time series data without relying on labels or clean versions of signals. The approach aims to mitigate the collapse issue that can occur when using self-supervised learning methods and strong augmentations. The proposed method is evaluated against state-of-the-art learning methods in three time series tasks, achieving performance improvements of more than 45-50%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to find patterns in noisy data without needing labels or special preparation. The researchers created a method that helps avoid a common problem called “collapse” where all the information gets lost. They tested their approach on three different tasks and found it works much better than other methods, improving results by 45-50%. |
Keywords
» Artificial intelligence » Self supervised » Time series
