kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Evaluating the Effects of Neural Noise in the Multidigraph Learning Rule
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
En Utvärdering av Effekterna av Neuralt Brus på ”Multidigraph Learning Rule” (Swedish)
Abstract [en]

There exists a knowledge gap in the field of Computational Neuroscience, where many learning models for neural networks fail to take into account the influence of neural noise. The purpose of this thesis was to address this knowledge gap by investigating the robustness of the Multidigraph learning rule (MDGL) when exposed to two kinds of neural noise: external noise and internal noise. The external noise was introduced as a random Poisson process in the form of network input. The internal noise was implemented by a Gaussian process and applied from within every recurrent neuron inside the network. A recurrent spiking neural network model was used. As a benchmark, the results for MDGL were compared to BPTT. The result showed that BPTT was more robust against both internal and external noise than MDGL. The accuracy and loss of the MDGL trained network were impacted negatively by both kinds of noise. Limitations in the work were small amounts of iterations in the simulations. Also, only a smaller fixed neural network was used, as opposed to neural networks of varying sizes.

Abstract [sv]

Det finns en kunskapslucka inom området beräkningsneurovetenskap där många inlärningsmodeller för neurala nätverk misslyckas med att ta hänsyn till påverkan av neuralt brus. Syftet med denna avhandling var att adressera denna kunskapslucka genom att undersöka robustheten hos Multidigraph learning rule (MDGL) när den utsätts för två typer av neuralt brus: externt brus och internt brus. Det externa bruset infördes som en slumpmässig Poisson-process i form av nätverksinmatning. Det interna bruset implementerades som en Gaussisk-process och applicerades från varje återkommande neuron inuti nätverket. Ett återkommande neuralt nätverk, med neuroner som kommunicerar genom aktionpotentialer, användes. Som referens jämfördes resultaten för MDGL med BPTT. Resultatet visade att BPTT var mer robust mot både internt och externt brus än MDGL. Noggrannheten och förlusten för nätverket tränat med MDGL påverkades negativt av båda typerna av brus. Begränsningar i arbetet var att antalet iterationer i simuleringarna var små. Dessutom användes endast ett mindre neuronnät av en enda storlek, istället för att använda flera neuronnät av varierande storlekar och uppsättningar.

Place, publisher, year, edition, pages
2023. , p. 29
Series
TRITA-EECS-EX ; 2023:264
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-330751OAI: oai:DiVA.org:kth-330751DiVA, id: diva2:1778350
Supervisors
Examiners
Available from: 2023-07-27 Created: 2023-07-01 Last updated: 2023-07-27Bibliographically approved

Open Access in DiVA

fulltext(3085 kB)131 downloads
File information
File name FULLTEXT01.pdfFile size 3085 kBChecksum SHA-512
894d7833ecae8e26cf8e88eeb6cc4c22351eb1b423deb8e118de30e274335d65760dbbb20d09c8158350058a62ca75a8f2d5af694c078d3f67bb171f415cdb84
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 131 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 279 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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