Differential radial basis function network for sequence modelling

Kojo Sarfo Gyamfi, James Brusey, Elena Gaura

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)
190 Downloads (Pure)


We propose a differential radial basis function (RBF) network termed RBF-DiffNet—whose hidden layer blocks are partial differential equations (PDEs) linear in terms of the RBF—to make the baseline RBF network robust to noise in sequential data. Assuming that the sequential data derives from the discretisation of the solution to an underlying PDE, the differential RBF network learns constant linear coefficients of the PDE, consequently regularising the RBF network by following modified backward-Euler updates. We experimentally validate the differential RBF network on the logistic map chaotic timeseries as well as on 30 real-world timeseries provided by Walmart in the M5 forecasting competition. The proposed model is compared with the normalised and unnormalised RBF networks, ARIMA, and ensembles of multilayer perceptrons (MLPs) and recurrent networks with long short-term memory (LSTM) blocks. From the experimental results, RBF-DiffNet consistently shows a marked reduction in the prediction error over the baseline RBF network (e.g., 41% reduction in the root mean squared scaled error on the M5 dataset, and 53% reduction in the mean absolute error on the logistic map); RBF-DiffNet also shows a comparable performance to the LSTM ensemble but requires 99% less computational time. Our proposed network consequently enables more accurate predictions—in the presence of observational noise—in sequence modelling tasks such as timeseries forecasting that leverage the model interpretability, fast training, and function approximation properties of the RBF network.
Original languageEnglish
Article number115982
JournalExpert Systems with Applications
Early online date13 Oct 2021
Publication statusPublished - 1 Mar 2022

Bibliographical note

Published under a Creative Commons Attribution (CC BY) licence - https://creativecommons.org/licenses/by/4.0/


EPSRC Grant: EP/S031863/1


  • Neural network
  • Radial basis function
  • Sequence modelling
  • Computer Science Applications
  • Artificial Intelligence
  • General Engineering

ASJC Scopus subject areas

  • Engineering(all)
  • Artificial Intelligence
  • Computer Science Applications


Dive into the research topics of 'Differential radial basis function network for sequence modelling'. Together they form a unique fingerprint.

Cite this