Developing machine-learning methods for the analysis of electromagnetic brain activity
Loading...
URL
Journal Title
Journal ISSN
Volume Title
School of Science |
Doctoral thesis (article-based)
| Defence date: 2021-04-23
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
2021
Major/Subject
Mcode
Degree programme
Language
en
Pages
78 + app. 44
Series
Aalto University publication series DOCTORAL DISSERTATIONS, 45/2021
Abstract
Traditionally, analysis of electromagnetic brain activity focuses on modeling the data-generating process and identifying which components in the measured signal are associated with experimental manipulations. At the beginning of XXI century, machine-learning based approaches aiming to infer brain states from the measurements started to gain increasing popularity. These methods rely on extracting complex multivariate patterns allowing to predict experimental conditions from the measurements. This thesis summarizes how such prediction-based methods can be applied to measurements of electromagnetic brain activity in a way that allows to advance our understanding of the underlying neural processes. Because these techniques belong to a class of inverse probability problems and do not model the data-generating process directly, interpreting the learning outcomes in terms of the underlying neurophysiological processes is not straightforward. Instead, predictive models allow testing the generalization properties of brain activity across e.g. experimental tasks (Publication I) and individuals (Publication II), as well as employ model comparison techniques to gain additional insights about the statistical properties of the data- generating process indirectly i.e. by comparing models with different structural constraints (Publication II). Moreover, projecting relevant model parameters learned from the data back into the input space can provide additional insights into the data-generating process and thus complement traditional approaches. These approaches are implemented in an open-sourceacademic software described in Publication III.Description
Supervising professor
Parkkonen, Lauri, Prof., Aalto University, Department of Neuroscience and Biomedical Engineering, FinlandThesis advisor
Parkkonen, Lauri, Prof., Aalto University, Department of Neuroscience and Biomedical Engineering, FinlandKeywords
MEG, machine learning, neuroscience
Other note
Parts
-
[Publication 1]: Ivan Zubarev and Lauri Parkkonen. Evidence for a general performance- monitoring system in the human brain. Human Brain Mapping, 39, 4322–4333, June 2018.
Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-201902252114DOI: 10.1002/hbm.24273 View at publisher
-
[Publication 2]: Ivan Zubarev, Rasmus Zetter, Hanna-Leena Halme and Lauri Parkkonen. Adaptive neural network classifier for decoding MEG signals. Neuroimage, 197, 425–434, May 2019.
Full text in Acris/Aaltodoc: http://urn.fi/URN:NBN:fi:aalto-201906033454DOI: 10.1016/j.neuroimage.2019.04.068 View at publisher
- [Publication 3]: Ivan Zubarev, Gavriela Vranou, Lauri Parkkonen. MNEflow: Neural networks for EEG/MEG decoding and interpretation. Submitted toSoftwareX, November 2020