Biologically Plausible Complex-Valued Neural Networks and Model Optimization

Ryan Yu*, Andrew Wood, Sarel Cohen, Moshick Hershcovitch, Daniel Waddington, Peter Chin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


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.

Original languageEnglish
Title of host publicationArtificial Intelligence Applications and Innovations - 18th IFIP WG 12.5 International Conference, AIAI 2022, Proceedings
EditorsIlias Maglogiannis, Lazaros Iliadis, John Macintyre, Paulo Cortez
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages14
ISBN (Print)9783031083327
StatePublished - 2022
Externally publishedYes
Event18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022 - Hersonissos, Greece
Duration: 17 Jun 202220 Jun 2022

Publication series

NameIFIP Advances in Information and Communication Technology
Volume646 IFIP
ISSN (Print)1868-4238
ISSN (Electronic)1868-422X


Conference18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022


Dive into the research topics of 'Biologically Plausible Complex-Valued Neural Networks and Model Optimization'. Together they form a unique fingerprint.

Cite this