Training methods for climate and neural network models
| dc.contributor | Aalto-yliopisto | fi |
| dc.contributor | Aalto University | en |
| dc.contributor.advisor | Kivinen, Jyri, Dr., Aalto University, Department of Computer Science, Finland | |
| dc.contributor.author | Abbas, Mudassar | |
| dc.contributor.department | Tietotekniikan laitos | fi |
| dc.contributor.department | Department of Computer Science | en |
| dc.contributor.lab | Complex Systems | en |
| dc.contributor.school | Perustieteiden korkeakoulu | fi |
| dc.contributor.school | School of Science | en |
| dc.contributor.supervisor | Kaski, Kimmo, Prof., Aalto University, Department of Computer Science, Finland | |
| dc.date.accessioned | 2018-10-25T09:03:19Z | |
| dc.date.available | 2018-10-25T09:03:19Z | |
| dc.date.defence | 2018-11-15 | |
| dc.date.issued | 2018 | |
| dc.description.abstract | When modeling complex phenomena in nature and in technological systems, one is often faced with the task of tuning/calibrating the models. In such cases, there typically exists a need for model parameter (and/or meta-parameter) value tuning for more effective modeling performance. Often such cannot be done manually, and in the machine learning approach, the tuning is done in an algorithmic and data-driven manner, and is called model training. The thesis presents studies in which such methods are adopted, in the contexts of climate and artificial neural networks, and proposes novel techniques. One of the studies is on the suitability of a well-known machine learning method called Bayesian optimization (BO), for parametric tuning of chaotic systems such as climate and numerical weatherprediction (NWP) models. The obtained results show that BO is a suitable method for such tuning tasks. A major desiderata for a trained machine learning model is the ability to generalize well to unseen data, and thus the phenomena such as (so-called) under- and overfitting are to be avoided. In this context, adopting (so-called) regularization methods as part of the model training process has become a standard procedure. In this thesis, we introduce a regularization framework that is shown to have close connections with many existing state-of-the-art regularization approaches. An adversarial variant, derived from the proposed regularization framework, is used for solving a classification task, and the obtained results are compared to those of other regularization methods. | en |
| dc.format.extent | 56 + app. 76 | |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.isbn | 978-952-60-8259-2 (electronic) | |
| dc.identifier.isbn | 978-952-60-8258-5 (printed) | |
| dc.identifier.issn | 1799-4942 (electronic) | |
| dc.identifier.issn | 1799-4934 (printed) | |
| dc.identifier.issn | 1799-4934 (ISSN-L) | |
| dc.identifier.uri | https://aaltodoc.aalto.fi/handle/123456789/34496 | |
| dc.identifier.urn | URN:ISBN:978-952-60-8259-2 | |
| dc.language.iso | en | en |
| dc.opn | Heikkonen, Jukka, Dr., University of Turku, Finland | |
| dc.publisher | Aalto University | en |
| dc.publisher | Aalto-yliopisto | fi |
| dc.relation.haspart | [Publication 1]: Solonen, A., Hakkarainen, J., Ilin, A., Abbas, M., Bibov, A. Estimating model error covariance matrix parameters in extended Kalman filtering. Nonlinear Processes in Geophysics, 21, 5, 919–927, 2014. DOI: 10.5194/npg-21-919-2014 | |
| dc.relation.haspart | [Publication 2]: Abbas, M., Ilin, A., Solonen, M., Hakkarainen, J., Oja, E., Järvinen, H. Bayesian optimization for tuning chaotic systems. Nonlin. Processes Geophys. Discuss., 1, 1283–1312, 2014. DOI: 10.5194/npgd-1-1283-2014 | |
| dc.relation.haspart | [Publication 3]: Abbas, M., Ilin, A., Solonen, M., Hakkarainen, J., Oja, E., Järvinen, H. Empirical evaluation of Bayesian optimization in parametric tuning of chaotic systems. Int. J. Uncertainty Quantification, 6, 6, 467–485, 2016. DOI: 10.1615/Int.J.UncertaintyQuantification.2016016645 | |
| dc.relation.haspart | [Publication 4]: Abbas, M., Kivinen, J., Raiko, T. Understanding regularization by virtual adversarial training, ladder networks and others. In International Conference on Learning Representations (ICLR) Workshop track, Puerto Rico, May 2016 | |
| dc.relation.ispartofseries | Aalto University publication series DOCTORAL DISSERTATIONS | en |
| dc.relation.ispartofseries | 209/2018 | |
| dc.rev | Roos, Teemu, Prof., University of Helsinki, Finland | |
| dc.rev | Pahikkala, Tapio, Prof., University of Turku, Finland | |
| dc.subject.keyword | chaotic systems | en |
| dc.subject.keyword | filtering | en |
| dc.subject.keyword | bayesian optimization | en |
| dc.subject.other | Computer science | en |
| dc.title | Training methods for climate and neural network models | en |
| dc.type | G5 Artikkeliväitöskirja | fi |
| dc.type.dcmitype | text | en |
| dc.type.ontasot | Doctoral dissertation (article-based) | en |
| dc.type.ontasot | Väitöskirja (artikkeli) | fi |
| local.aalto.acrisexportstatus | checked | |
| local.aalto.archive | yes | |
| local.aalto.formfolder | 2018_10_25_klo_11_54 |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- isbn9789526082592.pdf
- Size:
- 1012.99 KB
- Format:
- Adobe Portable Document Format
