Deeper Neural Networks with Non-Vanishing Logistic Hidden Units: NoVa vs. ReLU Neurons

Olaoluwa Adigun, Bart Kosko

Abstract: The new NoVa (nonvanishing) logistic neuron activation allows deeper neural networks because its derivative is positive. So it helps mitigate the problem of vanishing gradients in deep networks. Deep neural classifiers with NoVa hidden units had better classification accuracy on the CFAR-10, CFAR-100, and Caltech-256 image databases compared with threshold-linear ReLU hidden units. Still simpler identity hidden units also outperformed ReLU hidden units in deep classifiers but usually had less classification accuracy than NoVa networks. NoVa hidden neurons also outperformed ReLU hidden neurons in deep convolutional neural networks.