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

arXiv: https://arxiv.org/abs/2310.14720 · HTML: https://mlsanity.com/paper/2310.14720/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 44 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [Normalization Techniques in Training DNNs: Methodology, Analysis and Application](https://mlsanity.com/paper/2009.12836/) (2020)
- [Benchmark Dataset for Mid-Price Forecasting of Limit Order Book Data with Machine Learning Methods](https://mlsanity.com/paper/1705.03233/) (2017)
- [Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning](https://mlsanity.com/paper/2106.05956/) (2021)
- [Data Normalization for Bilinear Structures in High-Frequency Financial Time-series](https://mlsanity.com/paper/2003.00598/) (2020)
- [Normalization effects on deep neural networks](https://mlsanity.com/paper/2209.01018/) (2022)
- [The Kernel Density Integral Transformation](https://mlsanity.com/paper/2309.10194/) (2023)
- [Real Elliptically Skewed Distributions and Their Application to Robust Cluster Analysis](https://mlsanity.com/paper/2006.16671/) (2020)

## Built on by (most cited first, 2 of 2)

- [TOKON: TOKenization-Optimized Normalization for time series analysis with a large language model](https://mlsanity.com/paper/2502.05701/) (2025)
- [Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalization](https://mlsanity.com/paper/2504.10900/) (2025)

## Abstract (arXiv)

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.