Binary Multi Channel Morphological Neural Network
This work addresses the need for more explainable neural networks, particularly in domains like medical imaging, though it appears incremental as it builds upon existing convolutional neural networks.
The authors tackled the problem of limited theoretical understanding in deep learning by proposing a Binary Morphological Neural Network (BiMoNN) that combines neural networks with mathematical morphology for improved explainability, demonstrating equivalence to morphological operators and showing promising results in medical imaging.
Neural networks and particularly Deep learning have been comparatively little studied from the theoretical point of view. Conversely, Mathematical Morphology is a discipline with solid theoretical foundations. We combine these domains to propose a new type of neural architecture that is theoretically more explainable. We introduce a Binary Morphological Neural Network (BiMoNN) built upon the convolutional neural network. We design it for learning morphological networks with binary inputs and outputs. We demonstrate an equivalence between BiMoNNs and morphological operators that we can use to binarize entire networks. These can learn classical morphological operators and show promising results on a medical imaging application.