Dr Matthias Treder
Lecturer
School of Computer Science and Informatics
- trederm@cardiff.ac.uk
- +44 (0)29 2251 0960
- WX/3.12, Queen's Buildings - West Building Extension, 5 The Parade, Newport Road, Cardiff, CF24 3AA
My research interests revolve around machine learning, multivariate time-series analysis, and medical applications. I have been working in machine learning and its application in neuroscience and brain-computer interfaces since 2009.
I developed the open-source MVPA Light Toolbox for classification of neuroimaging time series data.
Education and qualifications
- 2017: BSc Mathematics, TU Berlin, Germany
- 2010: PhD in Cognitive Psychology
- 2005: Propedeuse diploma in Computer Science, Radboud University, The Netherlands
- 2004: MSc in Cognitive Psychology, Radboud University, The Netherlands
Honours and awards
- Travel Award, Guarantors of Brain Registered charity (2015)
- Brain-Computer Interfacing HCI 2011 Design Challenge, 1st prize (2011)
Academic positions
- 2018 - present: Lecturer, Cardiff University, UK
- 2017 - 2018: Research Fellow, Cardiff University, UK
- 2016 - 2017: Research Fellow, University of Birmingham, UK
- 2015 - 2016: DAAD (Germany) teaching fellow
- 2014 - 2015: Research Fellow, University of Cambridge, UK
- 2009 - 2014: Research Fellow, Machine Learning Lab, TU Berlin, Germany
Committees and reviewing
- Journal reviewer: IEEE TBME, J Neural Eng, NeuroImage
2019
- Krzeminski, D.et al. 2019. Classification of P300 component using a riemannian ensemble approach. Presented at: MEDICON 2019XV Mediterranean Conference on Medical and Biological Engineering and Computing, Coimbra, Portugal, 26-28 September 2019, Vol. 76. Springer Science Business Media, (10.1007/978-3-030-31635-8_229)
- Treder, M. 2019. Direct calculation of out-of-sample predictions in multi-class kernel FDA. Presented at: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 24-26 April 2019ESANN 2019 Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. ESANN pp. 245-250.
2018
- Treder, M. S. 2018. Improving SNR and reducing training time of classifiers in large datasets via kernel averaging. Lecture Notes in Computer Science 2018, pp. 239-248. (10.1007/978-3-030-05587-5_23)
- Tsvetanov, K. A.et al. 2018. Activity and connectivity differences underlying inhibitory control across the adult life span. Journal of Neuroscience 38(36), pp. 7887-7900. (10.1523/JNEUROSCI.2919-17.2018)
- Michelmann, S.et al. 2018. Data-driven re-referencing of intracranial EEG based on independent component analysis (ICA). Journal of Neuroscience Methods 307, pp. 125-137. (10.1016/j.jneumeth.2018.06.021)
- Ioannidis, K.et al. 2018. Problematic intemet use as an age-related multifaceted problem: Evidence from a two-site survey. Addictive Behaviors 81, pp. 157-166. (10.1016/j.addbeh.2018.02.017)
- Treder, M. 2018. Cross-validation in high-dimensional spaces: a lifeline for least-squares models and multi-class LDA. arXiv, article number: arXiv:1803.10016.
2017
- Price, D.et al. 2017. Age-related delay in visual and auditory evoked responses is mediated by white- and grey-matter differences. Nature Communications 8, article number: 15671. (10.1038/ncomms15671)
- Samu, D.et al. 2017. Preserved cognitive functions with age are determined by domain-dependent shifts in network responsivity. Nature Communications 8, article number: 14743. (10.1038/ncomms14743)
2016
- Ioannidis, K.et al. 2016. Problematic internet use (PIU): Associations with the impulsive-compulsive spectrum. An application of machine learning in psychiatry. Journal of Psychiatric Research 83, pp. 94-102. (10.1016/j.jpsychires.2016.08.010)
- Wolpe, N.et al. 2016. Ageing increases reliance on sensorimotor prediction through structural and functional differences in frontostriatal circuits. Nature Communications 7, article number: 13034. (10.1038/ncomms13034)
- Henson, R. N.et al. 2016. Multiple determinants of lifespan memory differences. Scientific Reports 6, article number: 32527. (10.1038/srep32527)
- Treder, M.et al. 2016. The LDA beamformer: Optimal estimation of ERP source time series using linear discriminant analysis. NeuroImage 129, pp. 279-291. (10.1016/j.neuroimage.2016.01.019)
2015
- Hwang, H.et al. 2015. A gaze independent brain-computer interface based on visual stimulation through closed eyelids. Scientific Reports 5(1), article number: 15890. (10.1038/srep15890)
2014
- Treder, M. S.et al. 2014. Decoding auditory attention to instruments in polyphonic music using single-trial EEG classification. Journal of Neural Engineering 11(2), article number: 26009. (10.1088/1741-2560/11/2/026009)
- Sonnleitner, A.et al. 2014. EEG alpha spindles and prolonged brake reaction times during auditory distraction in an on-road driving study. Accident Analysis and Prevention 62, pp. 110-118. (10.1016/j.aap.2013.08.026)
My teaching includes Python programming, statistical data analysis and visualisation.
Research interests include
- Interpretability of statistical models
- Kernel methods
- Optimisation in supervised learning
- Statistical learning in large datasets (many instances and/or many dimensions)
- Development of machine learning toolboxes
I am interested in supervising PhD students in the area of machine learning and data analysis, both fundamental and applied research. Specific topics include
- supervised learning
- optimisation
- time-series analysis
- applications in brain-computer interfaces
- applications in neuroimaging and psychiatry