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

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

Electronic Engineering

Research output: Contribution to conference › Abstract › peer-review

Abstract

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 language	English
Publication status	Published - 2023
Event	NNPC 2023: Natural, Neuromorphic & Physical Computing - Hanover, Germany Duration: 25 Oct 2023 → 27 Oct 2023

Conference

Conference	NNPC 2023
Country/Territory	Germany
City	Hanover
Period	25/10/23 → 27/10/23

Cite this

@conference{9b654a3c41bf40aea88aae9f7de5c9c9,

title = "Artificial Neural Microcircuits as Building Blocks for Neuromorphic Systems",

abstract = "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.",

author = "Andrew Walter and Shimeng Wu and Andy Tyrrell and Liam McDaid and Malachy McElholm and {Thandassery Sumithran}, Nidhin and Jim Harkin and Trefzer, {Martin Albrecht}",

year = "2023",

language = "English",

note = "NNPC 2023 : Natural, Neuromorphic & Physical Computing ; Conference date: 25-10-2023 Through 27-10-2023",

}

TY - CONF

T1 - Artificial Neural Microcircuits as Building Blocks for Neuromorphic Systems

AU - Walter, Andrew

AU - Wu, Shimeng

AU - Tyrrell, Andy

AU - McDaid, Liam

AU - McElholm, Malachy

AU - Thandassery Sumithran, Nidhin

AU - Harkin, Jim

AU - Trefzer, Martin Albrecht

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

M3 - Abstract

T2 - NNPC 2023

Y2 - 25 October 2023 through 27 October 2023

ER -