Univariate Radial Basis Function Layers: Brain-inspired Deep Neural Layers for Low-Dimensional Inputs - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

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

Résumé

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.
Fichier principal
Vignette du fichier
2311.16148.pdf (1.37 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04342724 , version 1 (13-12-2023)

Licence

Paternité

Identifiants

Citer

Basavasagar Patil, Xavier Alameda-Pineda, Chris Reinke. Univariate Radial Basis Function Layers: Brain-inspired Deep Neural Layers for Low-Dimensional Inputs. 2023. ⟨hal-04342724⟩
23 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More