Biologically Plausible Complex-Valued Neural Networks and Model Optimization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Biologically Plausible Complex-Valued Neural Networks and Model Optimization

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

Résumé

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.
Fichier sous embargo
Fichier sous embargo
0 5 16
Année Mois Jours
Avant la publication
mercredi 1 janvier 2025
Fichier sous embargo
mercredi 1 janvier 2025
Connectez-vous pour demander l'accès au fichier

Dates et versions

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

Licence

Identifiants

Citer

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⟩
23 Consultations
2 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More