Artificial Neural Microcircuits for use in Neuromorphic System Design

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

Artificial Neural Microcircuits for use in Neuromorphic System Design

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: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Artificial Neural Networks (ANNs) are one of the most widely employed forms of biomorphic computation. However (unlike the biological nervous systems they draw inspiration from) the current trend is for ANNs to be structurally homogeneous. Furthermore, this structural homogeneity requires the application of complex training & learning tools that produce application specific ANNs, susceptible to pitfalls like overfitting. In this paper, an alternative approach is suggested, inspired by the role played in biology by Neural Microcircuits, the so called “fundamental processing elements” of organic nervous systems. How large neural networks can be assembled using Artificial Neural Microcircuits, intended as off-the-shelf components, is articulated; before showing the results of initial work to produce a catalogue of such Microcircuits though the use of Novelty Search.

Original language	English
Title of host publication	ALife 2023: Ghost in the Machine
Subtitle of host publication	Proceedings
Publisher	MIT Press
Pages	51-58
Number of pages	8
Publication status	Published - 24 Jul 2023
Event	ALife 2023: Ghost in the Machine - University of Hokkaido , Sapporo, Japan Duration: 24 Jul 2023 → 28 Jul 2023

Conference

Conference	ALife 2023
Country/Territory	Japan
City	Sapporo
Period	24/07/23 → 28/07/23

Bibliographical note

This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.

Access to Document

Artificial Neural Microcircuits for use in Neuromorphic System Design
This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.
Accepted author manuscript, 858 KBLicence: CC BY

ALife 2023
Andrew Walter (Presenter)
24 Jul 2023 → 28 Jul 2023
Activity: Participating in or organising an event › Conference participation

Nervous Systems
Trefzer, M. A. & Tyrrell, A.
EPSRC
1/07/22 → 30/06/26
Project: Research project (funded) › Research

Cite this

@inproceedings{fb246864789e46858c5c05403517e85a,

title = "Artificial Neural Microcircuits for use in Neuromorphic System Design",

abstract = "Artificial Neural Networks (ANNs) are one of the most widely employed forms of biomorphic computation. However (unlike the biological nervous systems they draw inspiration from) the current trend is for ANNs to be structurally homogeneous. Furthermore, this structural homogeneity requires the application of complex training & learning tools that produce application specific ANNs, susceptible to pitfalls like overfitting. In this paper, an alternative approach is suggested, inspired by the role played in biology by Neural Microcircuits, the so called “fundamental processing elements” of organic nervous systems. How large neural networks can be assembled using Artificial Neural Microcircuits, intended as off-the-shelf components, is articulated; before showing the results of initial work to produce a catalogue of such Microcircuits though the use of Novelty Search. ",

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}",

note = "This is an author-produced version of the published paper. Uploaded in accordance with the University{\textquoteright}s Research Publications and Open Access policy. ; ALife 2023 : Ghost in the Machine ; Conference date: 24-07-2023 Through 28-07-2023",

year = "2023",

month = jul,

day = "24",

language = "English",

pages = "51--58",

booktitle = "ALife 2023: Ghost in the Machine",

publisher = "MIT Press ",

address = "United States",

}

TY - GEN

T1 - Artificial Neural Microcircuits for use in Neuromorphic System Design

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

N1 - This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.

PY - 2023/7/24

Y1 - 2023/7/24

N2 - Artificial Neural Networks (ANNs) are one of the most widely employed forms of biomorphic computation. However (unlike the biological nervous systems they draw inspiration from) the current trend is for ANNs to be structurally homogeneous. Furthermore, this structural homogeneity requires the application of complex training & learning tools that produce application specific ANNs, susceptible to pitfalls like overfitting. In this paper, an alternative approach is suggested, inspired by the role played in biology by Neural Microcircuits, the so called “fundamental processing elements” of organic nervous systems. How large neural networks can be assembled using Artificial Neural Microcircuits, intended as off-the-shelf components, is articulated; before showing the results of initial work to produce a catalogue of such Microcircuits though the use of Novelty Search.

AB - Artificial Neural Networks (ANNs) are one of the most widely employed forms of biomorphic computation. However (unlike the biological nervous systems they draw inspiration from) the current trend is for ANNs to be structurally homogeneous. Furthermore, this structural homogeneity requires the application of complex training & learning tools that produce application specific ANNs, susceptible to pitfalls like overfitting. In this paper, an alternative approach is suggested, inspired by the role played in biology by Neural Microcircuits, the so called “fundamental processing elements” of organic nervous systems. How large neural networks can be assembled using Artificial Neural Microcircuits, intended as off-the-shelf components, is articulated; before showing the results of initial work to produce a catalogue of such Microcircuits though the use of Novelty Search.

M3 - Conference contribution

SP - 51

EP - 58

BT - ALife 2023: Ghost in the Machine

PB - MIT Press

T2 - ALife 2023

Y2 - 24 July 2023 through 28 July 2023

ER -

Artificial Neural Microcircuits for use in Neuromorphic System Design

Abstract

Conference

Bibliographical note

Access to Document

Activities

ALife 2023

Projects

Nervous Systems

Cite this