Litcius/Paper detail

Geometric Back-propagation in Morphological Neural Networks

Rick Groenendijk, Leo Dorst, Theo Gevers

2023IEEE Transactions on Pattern Analysis and Machine Intelligence10 citationsDOIOpen Access PDF

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.

Topics & Concepts

Dilation (metric space)Mathematical morphologyConvolutional neural networkArtificial intelligenceArtificial neural networkComputer scienceBackpropagationConvergence (economics)Pattern recognition (psychology)Cellular neural networkAlgorithmComputer visionMathematicsGeometryImage processingImage (mathematics)EconomicsEconomic growthNeural Networks and ApplicationsTopological and Geometric Data AnalysisAdvanced Numerical Analysis Techniques
Geometric Back-propagation in Morphological Neural Networks | Litcius