تقرير
MorphoActivation: Generalizing ReLU activation function by mathematical morphology
العنوان: | MorphoActivation: Generalizing ReLU activation function by mathematical morphology |
---|---|
المؤلفون: | Velasco-Forero, Santiago, Angulo, Jesús |
المصدر: | International Conference on Discrete Geometry and Mathematical Morphology, Oct 2022, Strasbourg, France |
سنة النشر: | 2022 |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Discrete Mathematics, Electrical Engineering and Systems Science - Image and Video Processing, Electrical Engineering and Systems Science - Signal Processing, Statistics - Applications |
الوصف: | This paper analyses both nonlinear activation functions and spatial max-pooling for Deep Convolutional Neural Networks (DCNNs) by means of the algebraic basis of mathematical morphology. Additionally, a general family of activation functions is proposed by considering both max-pooling and nonlinear operators in the context of morphological representations. Experimental section validates the goodness of our approach on classical benchmarks for supervised learning by DCNN. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2207.06413 |
رقم الأكسشن: | edsarx.2207.06413 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!