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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jost, Daniel, Patil, Basavasagar, Alameda-Pineda, Xavier, Reinke, Chris
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910317413400576
author Jost, Daniel
Patil, Basavasagar
Alameda-Pineda, Xavier
Reinke, Chris
author_facet Jost, Daniel
Patil, Basavasagar
Alameda-Pineda, Xavier
Reinke, Chris
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16148
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Univariate Radial Basis Function Layers: Brain-inspired Deep Neural Layers for Low-Dimensional Inputs
Jost, Daniel
Patil, Basavasagar
Alameda-Pineda, Xavier
Reinke, Chris
Neural and Evolutionary Computing
Machine Learning
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.
title Univariate Radial Basis Function Layers: Brain-inspired Deep Neural Layers for Low-Dimensional Inputs
topic Neural and Evolutionary Computing
Machine Learning
url https://arxiv.org/abs/2311.16148