Open Access Repository

Techniques for Dealing with Missing Values in Feedforward Networks


Downloads per month over past year

Vamplew, P, Clark, David, Adams, A and Muench, J 1996 , 'Techniques for Dealing with Missing Values in Feedforward Networks', paper presented at the ACNN'96: The Seventh Australian Conference on Neural Networks, Canberra, ACT.

missingvaluesac...pdf | Download (213kB)
Available under University of Tasmania Standard License.

| Preview


Missing or incomplete data, a common reality, causes problems for artificial neural networks. In this paper we investigate several methods for dealing with missing values in feedforward networks. Reduced networks, substitution, estimation and expanded networks are applied to three data sets. We find that data sets vary in their sensitivity to missing values, and that reduced networks and estimation are the most effective ways of dealing with them.

Item Type: Conference or Workshop Item (Paper)
Authors/Creators:Vamplew, P and Clark, David and Adams, A and Muench, J
Keywords: Neural networks, missing data, missing inputs
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page