Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units

Abstract

We propose the Gaussian Error Linear Unit (GELU), a high-performing neural network activation function. The GELU nonlinearity is the expected transformation of a stochastic regularizer which randomly applies the identity or zero map, combining the intuitions of dropout and zoneout while respecting neuron values. This connection suggests a new probabilistic understanding of nonlinearities. We perform an empirical evaluation of the GELU nonlinearity against the ReLU and ELU activations and find performance improvements across all tasks.