Approximation Capabilities of Feedforward Neural Networks with GELU Activations
By: Konstantin Yakovlev, Nikita Puchkin
We derive an approximation error bound that holds simultaneously for a function and all its derivatives up to any prescribed order. The bounds apply to elementary functions, including multivariate polynomials, the exponential function, and the reciprocal function, and are obtained using feedforward neural networks with the Gaussian Error Linear Unit (GELU) activation. In addition, we report the network size, weight magnitudes, and behavior at infinity. Our analysis begins with a constructive approximation of multiplication, where we prove the simultaneous validity of error bounds over domains of increasing size for a given approximator. Leveraging this result, we obtain approximation guarantees for division and the exponential function, ensuring that all higher-order derivatives of the resulting approximators remain globally bounded.
Similar Papers
Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics
Machine Learning (CS)
Makes computer brains learn better and faster.
A Logical View of GNN-Style Computation and the Role of Activation Functions
Machine Learning (CS)
Makes AI understand complex patterns better.
Robust Deep Network Learning of Nonlinear Regression Tasks by Parametric Leaky Exponential Linear Units (LELUs) and a Diffusion Metric
Machine Learning (CS)
Makes computer learning better by fixing a math problem.