Generate Explanations for Time-series classification by ChatGPT

Zhechang Xue, 黄逸然, Hongnan Ma, Michael Beigl
July, 2024
PDF Cite Project Source Document
Image credit: Unsplash

Abstract

With the development of machine learning, the concept of explainability has gained increasing significance. It plays a crucial role in instilling trust among clients regarding the results generated by AI systems. Traditionally, researchers have relied on feature importance to explain why AI produces certain outcomes. However, this method has limitations. Despite the existence of documents that introduce various samples and describe formulas, comprehending the implicit meaning of these features remains challenging. As a result, establishing a clear and understandable connection between features and data can be a daunting task. In this paper, we aim to introduce a novel method for explaining time-series classification, leveraging the capabilities of ChatGPT to enhance the interpretability of results and foster a deeper understanding of feature contributions within time-series data.

Type
Conference paper
Publication
In The 2nd World Conference on eXplainable Artificial Intelligence
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

AutoML TinyML Wearable Computing Multiobjective Optimization Pervasive Sensing
黄逸然
黄逸然
Academic Associates

My research interests include Data Mining, XAI and Human Activity Recognition.