Geometric Back-Propagation in Morphological Neural Networks
| Authors | |
|---|---|
| Publication date | 11-2023 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | Issue number | 45 | 11 |
| Pages (from-to) | 14045-14051 |
| Organisations |
|
| 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. |
| Document type | Article |
| Language | English |
| Published at | https://doi.org/10.1109/TPAMI.2023.3290615 |
| Other links | https://www.scopus.com/pages/publications/85163468264 |
| Downloads |
Geometric Back-Propagation in Morphological Neural Networks
(Final published version)
|
| Permalink to this page | |
