The role of working memory mechanisms in speech recognition
| dc.contributor.advisor | Fitz, Hartmunt | |
| dc.contributor.advisor | Quaresima, Alessio | |
| dc.contributor.author | Kasper, Joost | |
| dc.date.issued | 2021-07-02 | |
| dc.description.abstract | Spiking neural networks are build from relevant neuro-biologically inspired mechanisms. Complex dynamics and network structures create models that can be used to make inferences about the existing knowledge pool on psycho-linguistics and neuroscience. This paper discusses working memory mechanisms and how they can be implemented in spiking neural models for a speech recognition task. Several mechanisms are discussed, that are all based on known phenomena in the brain. By comparing classi cation scores on states of the network during word representation, the performance of models with several working memory mechanisms is compared. These mechanisms are neuronal adaptation, implemented with an adaptive current, and short-term synaptic plasticity, implemented through a phenomenological model. It is concluded that the dynamics of the neuronal adaptation and short-term synaptic plasticity interact within the network. In particular, it is shown that the interactions between these mechanisms have di ering e ects on learning in the network. | |
| dc.identifier.uri | https://theses.ubn.ru.nl/handle/123456789/15734 | |
| dc.language.iso | en | |
| dc.thesis.faculty | Faculteit der Sociale Wetenschappen | |
| dc.thesis.specialisation | specialisations::Faculteit der Sociale Wetenschappen::Artificial Intelligence::Bachelor Artificial Intelligence | |
| dc.thesis.studyprogramme | studyprogrammes::Faculteit der Sociale Wetenschappen::Artificial Intelligence | |
| dc.thesis.type | Bachelor | |
| dc.title | The role of working memory mechanisms in speech recognition |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- Kasper, J. s-1017777-2021.pdf
- Size:
- 1.98 MB
- Format:
- Adobe Portable Document Format