Geometric Back-Propagation in Morphological Neural Networks.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 37384467.
- Also identified by DOI 10.1109/TPAMI.2023.3290615.
- 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
This paper provides a definition of back-propagation through geometric correspondences for morphological neural networks. In addition, dilation layers are shown to learn probe geometry by erosion of layer inputs and outputs. A proof-of-principle is provided, in which predictions and convergence of morphological networks significantly outperform convolutional networks.