English

Univariate Radial Basis Function Layers: Brain-inspired Deep Neural Layers for Low-Dimensional Inputs

Neural and Evolutionary Computing 2024-02-06 v2 Machine Learning

Abstract

Deep Neural Networks (DNNs) became the standard tool for function approximation with most of the introduced architectures being developed for high-dimensional input data. However, many real-world problems have low-dimensional inputs for which standard Multi-Layer Perceptrons (MLPs) are the default choice. An investigation into specialized architectures is missing. We propose a novel DNN layer called Univariate Radial Basis Function (U-RBF) layer as an alternative. Similar to sensory neurons in the brain, the U-RBF layer processes each individual input dimension with a population of neurons whose activations depend on different preferred input values. We verify its effectiveness compared to MLPs in low-dimensional function regressions and reinforcement learning tasks. The results show that the U-RBF is especially advantageous when the target function becomes complex and difficult to approximate.

Keywords

Cite

@article{arxiv.2311.16148,
  title  = {Univariate Radial Basis Function Layers: Brain-inspired Deep Neural Layers for Low-Dimensional Inputs},
  author = {Daniel Jost and Basavasagar Patil and Xavier Alameda-Pineda and Chris Reinke},
  journal= {arXiv preprint arXiv:2311.16148},
  year   = {2024}
}
R2 v1 2026-06-28T13:33:09.963Z