Processing of missing data by neural networks
Machine Learning
2019-04-05 v3 Machine Learning
Abstract
We propose a general, theoretically justified mechanism for processing missing data by neural networks. Our idea is to replace typical neuron's response in the first hidden layer by its expected value. This approach can be applied for various types of networks at minimal cost in their modification. Moreover, in contrast to recent approaches, it does not require complete data for training. Experimental results performed on different types of architectures show that our method gives better results than typical imputation strategies and other methods dedicated for incomplete data.
Cite
@article{arxiv.1805.07405,
title = {Processing of missing data by neural networks},
author = {Marek Smieja and Łukasz Struski and Jacek Tabor and Bartosz Zieliński and Przemysław Spurek},
journal= {arXiv preprint arXiv:1805.07405},
year = {2019}
}