{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/extended-deep-adaptive-input-normalization","title":"Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks","arxiv_id":"2310.14720","date":"2023-10-23","proceeding":null,"authors":["Marcus A. K. September","Francesco Sanna Passino","Leonie Goldmann","Anton Hinel"],"abstract":"Data preprocessing is a crucial part of any machine learning pipeline, and it can have a significant impact on both performance and training efficiency. This is especially evident when using deep neural networks for time series prediction and classification: real-world time series data often exhibit irregularities such as multi-modality, skewness and outliers, and the model performance can degrade rapidly if these characteristics are not adequately addressed. In this work, we propose the EDAIN (Extended Deep Adaptive Input Normalization) layer, a novel adaptive neural layer that learns how to appropriately normalize irregular time series data for a given task in an end-to-end fashion, instead of using a fixed normalization scheme. This is achieved by optimizing its unknown parameters simultaneously with the deep neural network using back-propagation. Our experiments, conducted using synthetic data, a credit default prediction dataset, and a large-scale limit order book benchmark dataset, demonstrate the superior performance of the EDAIN layer when compared to conventional normalization methods and existing adaptive time series preprocessing layers.","url_abs":"https://arxiv.org/abs/2310.14720v2","url_pdf":"https://arxiv.org/pdf/2310.14720v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"extended-deep-adaptive-input-normalization","repo_url":"https://github.com/marcusgh/edain_paper","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"irregular-time-series","task_name":"Irregular Time Series"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-prediction","task_name":"Time Series Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}