Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks

arXiv:2310.14720v2 Announce Type: replace
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 …

abstract arxiv classification cs.lg data data preprocessing efficiency impact machine machine learning networks neural networks normalization part performance pipeline prediction series stat.ml time series training type world