Change Point Detection With Conceptors logo

Change Point Detection With Conceptors

For the at most one change point problem, we propose the use of a conceptor matrix to learn the characteristic dynamics of a specified training window in a time series.

GitHub Link

The GitHub link is https://github.com/noahgade/changepointdetectionwithconceptors

Introduce

Title GitHub Repository for Change Point Detection Using Conceptors Summary The GitHub repository "ChangePointDetectionWithConceptors" by user noahgade focuses on Change Point Detection using Conceptors. It offers the R-package "conceptorCP" for implementing the methods detailed in the associated article. The repository includes simulated data for method evaluation, code to generate results and figures mentioned in the paper, as well as datasets and code for the application study in Section 5. For the at most one change point problem, we propose the use of a conceptor matrix to learn the characteristic dynamics of a specified training window in a time series.

Content

Repository includes:
  • R-package conceptorCP (link to GitHub page) containing code to perform the methods described in the article. (GNU zipped tar file)
  • Simulated data used to assess performance of change point methods. (.RData files)
  • Code used to generate results and figures discussed in paper. (.R file)
  • Data set used in application study Section 5. (.RData file)
  • Code used to assess the methods in the application study. (.R file)

Alternatives & Similar Tools

LongLLaMA-handle very long text contexts, up to 256,000 tokens logo

LongLLaMA is a large language model designed to handle very long text contexts, up to 256,000 tokens. It's based on OpenLLaMA and uses a technique called Focused Transformer (FoT) for training. The repository provides a smaller 3B version of LongLLaMA for free use. It can also be used as a replacement for LLaMA models with shorter contexts.