Best approximation by Heaviside perceptron networks.
other · Level V
Where this comes from
- Record sourced from PubMed, PMID 11152201.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
In Lp-spaces with p an integer from [1, infinity) there exists a best approximation mapping to the set of functions computable by Heaviside perceptron networks with n hidden units; however for p an integer from (1, infinity) such best approximation is not unique and cannot be continuous.
Medical subject headings
- Algorithms
- Neural Networks, Computer