Robust Deep Network Learning of Nonlinear Regression Tasks by Parametric Leaky Exponential Linear Units (LELUs) and a Diffusion Metric
This work addresses overfitting issues in deep learning for nonlinear regression tasks, but it appears incremental as it builds on existing activation functions like ELU and Leaky-RELU.
The paper tackles the problem of overfitting and sensitivity in deep networks for nonlinear regression by proposing a smooth, trainable activation function called Leaky Exponential Linear Unit (LELU) and a diffusion-loss metric. It demonstrates improved performance, though no concrete numbers are provided in the abstract.
This document proposes a parametric activation function (ac.f.) aimed at improving multidimensional nonlinear data regression. It is a established knowledge that nonlinear ac.f's are required for learning nonlinear datasets. This work shows that smoothness and gradient properties of the ac.f. further impact the performance of large neural networks in terms of overfitting and sensitivity to model parameters. Smooth but vanishing-gradient ac.f's such as ELU or SiLU (Swish) have limited performance and non-smooth ac.f's such as RELU and Leaky-RELU further impart discontinuity in the trained model. Improved performance is demonstrated with a smooth "Leaky Exponential Linear Unit", with non-zero gradient that can be trained. A novel diffusion-loss metric is also proposed to gauge the performance of the trained models in terms of overfitting.