eprintid: 10058961 rev_number: 17 eprint_status: archive userid: 608 dir: disk0/10/05/89/61 datestamp: 2018-10-25 14:58:54 lastmod: 2021-09-28 22:27:17 status_changed: 2018-10-25 14:58:54 type: proceedings_section metadata_visibility: show creators_name: Ferreira, FS creators_name: Rosa, MJ creators_name: Moutoussis, M creators_name: Dolan, R creators_name: Shawe-Taylor, J creators_name: Ashburner, J creators_name: Mourao-Miranda, J title: Sparse PLS hyper-parameters optimisation for investigating brain-behaviour relationships ispublished: pub divisions: UCL divisions: B02 divisions: C07 divisions: D07 divisions: F83 divisions: B04 divisions: C05 divisions: F48 keywords: Tuning parameters; High-dimensionality; Brainbehaviour; Regularisation; Sparse PLS note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Unsupervised learning approaches, such as Partial Least Squares, can be used to investigate relationships between multiple sources of data, such as neuroimaging and behavioural data. In cases of high-dimensional datasets with limited number of examples (e.g. neuroimaging data) there is a need for regularisation to enable the solution of the ill-posed problem and prevent overfitting. Different approaches have been proposed to optimise the regularisation parameters in unsupervised models, however, so far, there has been no comparison between the different approaches using the same data. In this work, two optimisation frameworks (i.e. a permutation and a train/test framework) were compared using sparse PLS to investigate associations between brain connectivity and behaviour data. Both frameworks were able to identify at least one brain-behaviour associative effect. A second brain-behaviour effect was only found using the train/test framework. More importantly, the results show that the multivariate associative effects found with the train/test framework generalise better to new data, suggesting that results based on the permutation framework should be carefully interpreted. date: 2018 date_type: published publisher: IEEE official_url: https://doi.org/10.1109/PRNI.2018.8423947 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1576491 doi: 10.1109/PRNI.2018.8423947 isbn_13: 9781538668597 lyricists_name: Ashburner, John lyricists_name: Dolan, Raymond lyricists_name: Mourao-Miranda, Janaina lyricists_name: Moutoussis, Michael lyricists_name: Santos Ferreira, Fabio lyricists_name: Shawe-Taylor, John lyricists_id: JTASH57 lyricists_id: RJDOL46 lyricists_id: JMOUR63 lyricists_id: MMOUT81 lyricists_id: FDSFE64 lyricists_id: JSHAW87 actors_name: Santos Ferreira, Fabio actors_id: FDSFE64 actors_role: owner full_text_status: public publication: 2018 International Workshop on Pattern Recognition in Neuroimaging, PRNI 2018 event_title: 2018 International Workshop on Pattern Recognition in Neuroimaging (PRNI), 12-14 June 2018, Singapore book_title: 2018 International Workshop on Pattern Recognition in Neuroimaging (PRNI) citation: Ferreira, FS; Rosa, MJ; Moutoussis, M; Dolan, R; Shawe-Taylor, J; Ashburner, J; Mourao-Miranda, J; (2018) Sparse PLS hyper-parameters optimisation for investigating brain-behaviour relationships. In: 2018 International Workshop on Pattern Recognition in Neuroimaging (PRNI). IEEE Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10058961/1/FerreiraFS_PRNI2018.pdf