Biologically Plausible Complex-Valued Neural Networks and Model Optimization - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2022

Biologically Plausible Complex-Valued Neural Networks and Model Optimization

Ryan Yu
  • Function : Author
  • PersonId : 1318743
Andrew Wood
  • Function : Author
  • PersonId : 1318744
Sarel Cohen
Moshick Hershcovitch
  • Function : Author
  • PersonId : 1318746
Daniel Waddington
  • Function : Author
  • PersonId : 1318747
Peter Chin
  • Function : Author
  • PersonId : 1318748

Abstract

Artificial Neural Networks (ANNs) are thinly based on biological neural pathways. In an ANN, each node computes its activation by applying a non-linearity to a weighted sum of its inputs. While this formulation has been wildly successful for a variety of tasks, it is still a far cry from its biological counterpart, largely due to ANNs lack of phase information during computation. In this paper, we adapt ANNs to operate on complex values which naturally allows the inclusion of phase information during the forward pass. We demonstrate that our complex-valued architecture generally performs better compared to real-valued and other complex-valued networks in similar conditions. Additionally, we couple our model with a biologically inspired form of dimensionality reduction and present our findings on the MNIST and MusicNet data sets.
Embargoed file
Embargoed file
0 7 18
Year Month Jours
Avant la publication
Wednesday, January 1, 2025
Embargoed file
Wednesday, January 1, 2025
Please log in to request access to the document

Dates and versions

hal-04317193 , version 1 (01-12-2023)

Licence

Attribution

Identifiers

Cite

Ryan Yu, Andrew Wood, Sarel Cohen, Moshick Hershcovitch, Daniel Waddington, et al.. Biologically Plausible Complex-Valued Neural Networks and Model Optimization. 18th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2022, Hersonissos, Greece. pp.369-382, ⟨10.1007/978-3-031-08333-4_30⟩. ⟨hal-04317193⟩
21 View
1 Download

Altmetric

Share

Gmail Facebook X LinkedIn More