Bipolar morphological neural networks: convolution without multiplication

Elena Limonova; Daniil Matveev; Dmitry Nikolaev; Vladimir V. Arlazarov

doi:10.1117/12.2559299

31 January 2020 Bipolar morphological neural networks: convolution without multiplication

Elena Limonova, Daniil Matveev, Dmitry Nikolaev, Vladimir V. Arlazarov

Proceedings Volume 11433, Twelfth International Conference on Machine Vision (ICMV 2019); 114333J (2020) https://doi.org/10.1117/12.2559299
Event: Twelfth International Conference on Machine Vision, 2019, Amsterdam, Netherlands

Abstract

In the paper we introduce a novel bipolar morphological neuron and bipolar morphological layer models. The models use only such operations as addition, subtraction and maximum inside the neuron and exponent and logarithm as activation functions for the layer. The proposed models unlike previously introduced morphological neural networks approximate the classical computations and show better recognition results. We also propose layer-by-layer approach to train the bipolar morphological networks, which can be further developed to an incremental approach for separate neurons to get higher accuracy. Both these approaches do not require special training algorithms and can use a variety of gradient descent methods. To demonstrate efficiency of the proposed model we consider classical convolutional neural networks and convert the pre-trained convolutional layers to the bipolar morphological layers. Seeing that the experiments on recognition of MNIST and MRZ symbols show only moderate decrease of accuracy after conversion and training, bipolar neuron model can provide faster inference and be very useful in mobile and embedded systems.

Citation Download Citation

Elena Limonova, Daniil Matveev, Dmitry Nikolaev, and Vladimir V. Arlazarov "Bipolar morphological neural networks: convolution without multiplication", Proc. SPIE 11433, Twelfth International Conference on Machine Vision (ICMV 2019), 114333J (31 January 2020); https://doi.org/10.1117/12.2559299

ACCESS THE FULL ARTICLE