Advancing system performance with redundancy: From biological to artificial designs

Anh Tuan Nguyen, Jian Xu, Diu Khue Luu, Qi Zhao, Zhi Yang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Redundancy is a fundamental characteristic of many biological processes such as those in the genetic, visual, muscular, and nervous systems, yet its driven mechanism has not been fully comprehended. Until recently, the only understanding of redundancy is as a mean to attain fault tolerance, which is reflected in the design of many man-made systems. On the contrary, our previous work on redundant sensing (RS) has demonstrated an example where redundancy can be engineered solely for enhancing accuracy and precision. The design was inspired by the binocular structure of human vision, which we believe may share a similar operation. In this letter, we present a unified theory describing how such utilization of redundancy is feasible through two complementary mechanisms: representational redundancy (RPR) and entangled redundancy (ETR). We also point out two additional examples where our new understanding of redundancy can be applied to justify a system's superior performance. One is the human musculoskeletal system (HMS), a biological instance, and the other is the deep residual neural network (ResNet), an artificial counterpart. We envision that our theory would provide a framework for the future development of bio-inspired redundant artificial systems, as well as assist studies of the fundamental mechanisms governing various biological processes.

Original languageEnglish (US)
Pages (from-to)555-573
Number of pages19
JournalNeural computation
Volume31
Issue number3
DOIs
StatePublished - Mar 1 2019

Fingerprint

Biological Phenomena
Musculoskeletal System
Nervous System
Artificial
Redundancy

PubMed: MeSH publication types

  • Journal Article

Cite this

Advancing system performance with redundancy : From biological to artificial designs. / Nguyen, Anh Tuan; Xu, Jian; Luu, Diu Khue; Zhao, Qi; Yang, Zhi.

In: Neural computation, Vol. 31, No. 3, 01.03.2019, p. 555-573.

Research output: Contribution to journalArticle

@article{edb00055b9224c439ecaedf4a0c95120,
title = "Advancing system performance with redundancy: From biological to artificial designs",
abstract = "Redundancy is a fundamental characteristic of many biological processes such as those in the genetic, visual, muscular, and nervous systems, yet its driven mechanism has not been fully comprehended. Until recently, the only understanding of redundancy is as a mean to attain fault tolerance, which is reflected in the design of many man-made systems. On the contrary, our previous work on redundant sensing (RS) has demonstrated an example where redundancy can be engineered solely for enhancing accuracy and precision. The design was inspired by the binocular structure of human vision, which we believe may share a similar operation. In this letter, we present a unified theory describing how such utilization of redundancy is feasible through two complementary mechanisms: representational redundancy (RPR) and entangled redundancy (ETR). We also point out two additional examples where our new understanding of redundancy can be applied to justify a system's superior performance. One is the human musculoskeletal system (HMS), a biological instance, and the other is the deep residual neural network (ResNet), an artificial counterpart. We envision that our theory would provide a framework for the future development of bio-inspired redundant artificial systems, as well as assist studies of the fundamental mechanisms governing various biological processes.",
author = "Nguyen, {Anh Tuan} and Jian Xu and Luu, {Diu Khue} and Qi Zhao and Zhi Yang",
year = "2019",
month = "3",
day = "1",
doi = "10.1162/neco_a_01166",
language = "English (US)",
volume = "31",
pages = "555--573",
journal = "Neural Computation",
issn = "0899-7667",
publisher = "MIT Press Journals",
number = "3",

}

TY - JOUR

T1 - Advancing system performance with redundancy

T2 - From biological to artificial designs

AU - Nguyen, Anh Tuan

AU - Xu, Jian

AU - Luu, Diu Khue

AU - Zhao, Qi

AU - Yang, Zhi

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Redundancy is a fundamental characteristic of many biological processes such as those in the genetic, visual, muscular, and nervous systems, yet its driven mechanism has not been fully comprehended. Until recently, the only understanding of redundancy is as a mean to attain fault tolerance, which is reflected in the design of many man-made systems. On the contrary, our previous work on redundant sensing (RS) has demonstrated an example where redundancy can be engineered solely for enhancing accuracy and precision. The design was inspired by the binocular structure of human vision, which we believe may share a similar operation. In this letter, we present a unified theory describing how such utilization of redundancy is feasible through two complementary mechanisms: representational redundancy (RPR) and entangled redundancy (ETR). We also point out two additional examples where our new understanding of redundancy can be applied to justify a system's superior performance. One is the human musculoskeletal system (HMS), a biological instance, and the other is the deep residual neural network (ResNet), an artificial counterpart. We envision that our theory would provide a framework for the future development of bio-inspired redundant artificial systems, as well as assist studies of the fundamental mechanisms governing various biological processes.

AB - Redundancy is a fundamental characteristic of many biological processes such as those in the genetic, visual, muscular, and nervous systems, yet its driven mechanism has not been fully comprehended. Until recently, the only understanding of redundancy is as a mean to attain fault tolerance, which is reflected in the design of many man-made systems. On the contrary, our previous work on redundant sensing (RS) has demonstrated an example where redundancy can be engineered solely for enhancing accuracy and precision. The design was inspired by the binocular structure of human vision, which we believe may share a similar operation. In this letter, we present a unified theory describing how such utilization of redundancy is feasible through two complementary mechanisms: representational redundancy (RPR) and entangled redundancy (ETR). We also point out two additional examples where our new understanding of redundancy can be applied to justify a system's superior performance. One is the human musculoskeletal system (HMS), a biological instance, and the other is the deep residual neural network (ResNet), an artificial counterpart. We envision that our theory would provide a framework for the future development of bio-inspired redundant artificial systems, as well as assist studies of the fundamental mechanisms governing various biological processes.

UR - http://www.scopus.com/inward/record.url?scp=85061607160&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061607160&partnerID=8YFLogxK

U2 - 10.1162/neco_a_01166

DO - 10.1162/neco_a_01166

M3 - Article

C2 - 30645181

AN - SCOPUS:85061607160

VL - 31

SP - 555

EP - 573

JO - Neural Computation

JF - Neural Computation

SN - 0899-7667

IS - 3

ER -