MorphoActivation: Generalizing ReLU activation function by mathematical morphology

07/13/2022
by   Santiago Velasco-Forero, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset