Artificial Neural Microcircuits as Building Blocks for Neuromorphic Systems

Andrew Walter*, Shimeng Wu, Andy Tyrrell, Liam McDaid, Malachy McElholm, Nidhin Thandassery Sumithran, Jim Harkin, Martin Albrecht Trefzer

*Corresponding author for this work

Research output: Contribution to conferenceAbstractpeer-review


Artificial Neural Networks (ANNs) are the most widely employed forms of neuromorphic computation. However, unlike the biological systems they draw inspiration from, the current standard is for ANNs to be structurally homogeneous. This is at odds with research evidencing that structure plays a significant role in supporting learning capability and function of the brain. In this paper, an alternative approach inspired by biological Neural Microcircuits is suggested. The conceit of assembling ANNs using a catalogue of Artificial Neural Microcircuits, and a methodology to assemble said catalogue, is articulated; before showing the results of initial work to produce such a catalogue.
Original languageEnglish
Publication statusPublished - 2023
EventNNPC 2023: Natural, Neuromorphic & Physical Computing - Hanover, Germany
Duration: 25 Oct 202327 Oct 2023


ConferenceNNPC 2023

Cite this