Year: 2018
Type: preprint
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.
Source: arXiv (Cornell University)
Institution: Jagiellonian University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Narodowe Centrum Nauki
Awards: G323413916, G6344475819
OpenAlex ID: W2803448608
