Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The role of ambient noise in the evolution of robust mental representations in cognitive systems
Michigan State University, East Lansing, United States.ORCID iD: 0000-0002-4872-1961
2020 (English)In: Proceedings of the 2019 Conference on Artificial Life: How Can Artificial Life Help Solve Societal Challenges, ALIFE 2019, MIT Press , 2020, p. 432-439Conference paper (Refereed)
Abstract [en]

Natural environments are full of ambient noise; nevertheless, natural cognitive systems deal greatly with uncertainty but also have ways to suppress or ignore noise unrelated to the task at hand. For most intelligent tasks, experiences and observations have to be committed to memory and these representations of reality inform future decisions. We know that deep learned artificial neural networks (ANNs) often struggle with the formation of representations. This struggle may be due to the ANN's fully interconnected, layered architecture. This forces information to be propagated over the entire system, which is different from natural brains that instead have sparsely distributed representations. Here we show how ambient noise causes neural substrates such as recurrent ANNs and long short-term memory neural networks to evolve more representations in order to function in these noisy environments, which also greatly improves their functionality. However, these systems also tend to further smear their representations over their internal states making them more vulnerable to internal noise. We also show that Markov Brains (MBs) are mostly unaffected by ambient noise, and their representations remain sparsely distributed (i.e. not smeared). This suggests that ambient noise helps to increase the amount of representations formed in neural networks, but also requires us to find additional solutions to prevent smearing of said representations. Copyright © ALIFE 2019.All rights reserved.

Place, publisher, year, edition, pages
MIT Press , 2020. p. 432-439
Keywords [en]
Acoustic noise, Brain, Recurrent neural networks, Distributed representation, Internal noise, Internal state, Layered architecture, Mental representations, Natural environments, Neural substrates, Noisy environment, Cognitive systems
National Category
Evolutionary Biology Computer Sciences
Identifiers
URN: urn:nbn:se:du-37156Scopus ID: 2-s2.0-85085035887OAI: oai:DiVA.org:du-37156DiVA, id: diva2:1557932
Conference
2019 Conference on Artificial Life: How Can Artificial Life Help Solve Societal Challenges, ALIFE 2019, 29 July 2019 - 2 August 2019
Available from: 2021-05-27 Created: 2021-05-27 Last updated: 2021-05-27Bibliographically approved

Open Access in DiVA

No full text in DiVA

Scopus

Authority records

Hintze, Arend

Search in DiVA

By author/editor
Hintze, Arend
Evolutionary BiologyComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 13 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf