论文标题
二进制多通道形态神经网络
Binary Multi Channel Morphological Neural Network
论文作者
论文摘要
从理论的角度来看，神经网络尤其是深度学习的研究很少。相反，数学形态是具有坚实理论基础的学科。我们将这些域结合起来，提出一种新型的神经结构，从理论上讲是可以解释的。我们引入了建立在卷积神经网络基于的二元形态神经网络（Bimonn）。我们设计用于学习具有二进制输入和输出的形态网络。我们证明了Bimonns和形态运算符之间的等效性，我们可以用来将整个网络二重化。这些可以学习经典的形态操作员，并在医学成像应用中显示出令人鼓舞的结果。
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.
