About

Understanding how mind emerges from matter is one of the great remaining questions in science. How is it possible that organized clumps of matter such as our own brains give rise to all of our beliefs, desires 
and intentions, ultimately allowing us to contemplate ourselves as well as the universe from which we originate?

The Artificial Cognitive Systems lab investigates the computational principles and neural mechanisms that mediate natural intelligence. To this end, we combine computational modelling, which has its roots in artificial intelligence and computational neuroscience, with empirical research, where we collect neural and behavioural data as people engage in challenging cognitive tasks.

Ultimately, our aim is to create intelligent machines that think like people by combining insights from multiple fields of research. From an applied perspective we are interested in using intelligent machines to address societal challenges.

  • Prof. dr. Marcel van Gerven
  • Department of Artificial Intelligence
  • Donders Centre for Cognition
  • Donders Institute for Brain, Cognition and Behaviour
  • Radboud University
  •   m.vangerven@donders.ru.nl
  •   +31 24 365 59 31
  •   +31 24 365 27 28
  •   PO Box 9104 6500 HE Nijmegen the Netherlands
  •   SP B 03.46 Montessorilaan 3 6525 HR Nijmegen the Netherlands

Our lab is physically located at the Donders Centre for Cognition, Spinoza building, Montessorilaan 3, Nijmegen, The Netherlands. When entering the Spinoza building, you should proceed to room B.03.46 at the third floor of the B wing (low-rise part of the building). Please contact the front desk for more specific directions once you arrive. You can reach the Spinoza building via public transport.

Current Members

  • image

    Marcel van Gerven

    Principal Investigator

    I am interested in the computational principles that underly adaptive behaviour. The questions that I focus on are how the brain is able to extract information from its environment and use this information in order to generate optimal actions. My main goal is to develop biologically plausible neural network models that further our understanding of natural intelligence and provide a route towards solving the strong AI problem.

  • image

    Sander Bosch

    Postdoc

    I use computational models on (high-field) fMRI and MEG to investigate the neural mechanisms underlying perception and memory. Specifically, I am interested in how these bottom-up and top-down processes are implemented and interact in the human brain.

  • image

    Linda Geerligs

    Postdoc

    I am working on my Veni project together with with Marcel van Gerven, Pieter Medendorp and Roy Kessels. My work focuses on the relation between functional and structural changes in the aging brain and their joint association with cognition.

  • image

    Umut Güçlü

    Postdoc

    My primary research interest is in developing computational models of (ultra-high-field) fMRI and MEG data to characterize the relationship between cognitive processes and brain connectivity. Besides brain connectivity, I am also interested in neural coding, unsupervised feature learning and deep learning.

  • image

    Yağmur Güçlütürk

    Postdoc

    I am working on the NEuronal STimulatiOn for Recovery of function (NESTOR) project with Richard van Wezel and Marcel van Gerven for developing cortical implants to restore sight in blind. In this project, I am developing computer vision models that transform camera input into meaningful phosphene patterns, as well as developing AR/VR simulations of phosphene vision, and running psychophysical experiments.

  • image

    Max Hinne

    Postdoc

    I am interested in structural and functional brain connectivity. In particular I study different (probabilistic) generative models and develop techniques efficiently compute them. Two central themes in my research are integration of different imaging modalities (e.g. fMRI and dMRI) and explicit modeling of uncertainty in connectivity estimates.

  • image

    Andrew Reid

    Postdoc

    I have a strong interest in developing methods through which connectivity estimates derived from multiple modalities can be compared and integrated. My present focus involves combining MRI and MEG evidence to evaluate how neuromodulatory systems interact with hippocampal and cortical circuits to produce cognition, and how this may break down in neurodegenerative diseases such as Alzheimer’s.

  • image

    Nadine Dijkstra

    PhD Student

    I am mainly interested in visual experience in the absence of visual input. During my PhD I will investigate to what extent visual imagery relies on the same neural mechanisms as visual perception. Besides neuroscience, I also have a strong interest in philosophy of mind and consciousness.

  • image

    Silvan Quax

    PhD Student

    How does the brain extract complex features and concepts from the information entering our senses? I am particularly interested in how individual neurons, forming a complex network, can perform this task. I apply computational models to experimental data of high temporal resolution to unravel the dynamics of the mechanisms involved in this process.

  • image

    Gabi Ras

    PhD Student

    I apply deep neural networks to affective computing for use in robotics, focusing on methods for the interpretability of black-box machine learning algorithms and aiming to improve human-robot interaction.

  • image

    Katja Seeliger

    PhD Student

    I am focusing on encoding and decoding models. One major topic is identifying biologically plausible feature transformations by investigating to what extent deep learning can predict human perceptual processing. I also work on the optimisation of this mapping and its inversion using statistical machine learning techniques.

  • image

    Jordy Thielen

    PhD Student

    Visual sensory information, as we receive it on our retina, mainly contains partially hidden objects. Instead of perceiving them as fragmented, we perceive them as completed objects. I am interested in how the brain achieves this amodal completion, and how it (and its underlying neural mechanism) is related to other phenomena such as modal completion and imagery.

  • image

    Erdi Çallı

    Research Assistant

    I develop deep neural networks (models) that work on mobile devices. My work involves researching and developing models, reducing their computational footprint, and developing mobile applications that make use of them.

Master Students

  • Michele D’Asaro (supervisors: Silvan, Marcel)
  • Hugo Dictus (supervisors: Katja, Silvan, Marcel)
  • Patrick Ebel (supervisors: Max)
  • Wieke Kanters (supervisors: Max, Marcel)
  • Filippos Panagiotou (supervisors: Luca, Marcel)
  • Josh Ring (supervisors: Marcel)
  • Marjolein Troost (supervisors: Katja, Marcel)
  • Inez Wijnands (supervisors: Ronald, Max)
  • Marcel Zuur (supervisors: Silvan, Marcel)

Alumni

  • Ali Bahramisharif
  • Ronald Janssen
  • Haiteng Jiang
  • Pasi Jylänki
  • Claudia Lüttke
  • Sanne Schoenmakers
  • Elena Shumskaya
  • Irina Simanova

Preprints

  1. Ambrogioni, L., Güçlü, U., van Gerven, M.A.J., Maris, E., 2017. The kernel mixture network: A nonparametric method for conditional density estimation of continuous random variables. arXiv. arXiv:1705.07111 [stat.ML], 1–10.
  2. Güçlü, U., Güçlütürk, Y., Madadi, M., Escalera, S., Baró, X., González, J., van Lier, R., van Gerven, M.A.J., 2017. End-to-end semantic face segmentation with conditional random fields as convolutional, recurrent and adversarial networks ArXiv. arXiv:1703.03305 [cs.CV]. 1–18.
  3. Ambrogioni, L., Umut, G., Maris, E., van Gerven, M..A.J. 2017. Estimating nonlinear dynamics with the ConvNet smoother ArXiv. arXiv:1702.05243 [stat.ML]. 1–8.

Journal papers

  1. Gucluturk, Y., Guclu, U., Baro, X., Escalante, H. J., Guyon, I., Escalera, S., … Lier, R. Van. (2017). Multimodal first impression analysis with deep residual networks. IEEE Trans Eff Comput, 99, 1–14. http://doi.org/10.1007/978-3-319-49409-8
  2. Hirschmann, J., Schoffelen, J. M., Schnitzler, A., & van Gerven, M. A. J. (2017). Parkinsonian rest tremor can be detected accurately based on neuronal oscillations recorded from the subthalamic nucleus. Clinical Neurophysiology. http://doi.org/10.1016/j.clinph.2017.07.419
  3. Seeliger, K., Fritsche, M., Güçlü, U., Schoenmakers, S., Schoffelen, J., Bosch, S. E., & Gerven, M. A. J. Van. (2017). Convolutional neural network-based encoding and decoding of visual object recognition in space and time. NeuroImage, doi: 10.1016/j.neuroimage.2017.07.018. http://doi.org/10.1016/j.neuroimage.2017.07.018
  4. Berezutskaya, J., Freudenburg, Z. V, Güçlü, U., van Gerven, M. A. J., & Ramsey, N. F. (2017). Neural tuning to low-level features of speech throughout the perisylvian cortex. J Neurosci, 10.1523/JNEUROSCI.0238-17.2017.
  5. Dijkstra, N., Zeidman, P., Ondobaka, S., Gerven, M. A. J. Van, and Friston, K. (2017). Distinct top-down and bottom-up brain connectivity during visual perception and imagery. Scientific Reports, 7(5677), 1–9. http://doi.org/10.1038/s41598-017-05888-8.
  6. Ambrogioni, L., Gerven, M.A.J. Van, Maris, E., 2017. Dynamic decomposition of spatiotemporal neural signals. PLoS Comp. Biol. 13(5), e1005540.
  7. Benozzo, D., Jylanki, P., Olivetti, E., Avesani, P., van Gerven, M.A.J., 2017. Bayesian estimation of directed functional coupling from brain recordings. PLoS One 12, e0177359.
  8. Dijkstra, N., Bosch, S., van Gerven, MAJ, 2017. Vividness of visual imagery depends on the neural overlap with perception in visual areas. J. Neurosci. In Press.
  9. Hinne, M, Meijers, A, Bakker, R, Tiesinga, PHE, Morup, M, van Gerven, MAJ, 2017. The missing link : Predicting connectomes from noisy and partially observed tract tracing data. PLoS Comp. Biol. 1–22. doi:10.1371/journal.pcbi.1005374
  10. Güçlü, U., Gerven, M., 2017. Modeling the dynamics of human brain activity with recurrent neural networks. J. Front. Comput. Neurosci. 11. doi:10.3389/fncom.2017.00007
  11. Janssen, RJ, Jylänki, P, van Gerven, MAJ, 2016. Let’s not waste time: Using temporal information in clustered activity estimation with spatial adjacency restrictions (CAESAR) for parcellating fMRI data. PLoS ONE, 11(12): 11(12): e0164703.
  12. Shumskaya, E, van Gerven, MAJ, Norris, DG, Vos, PE, Kessels, RPC, 2016. Abnormal connectivity in the sensorimotor network predicts attention deficits in traumatic brain injury. Experimental Brain Research. In Press.
  13. Janssen, MAM, Hinne, M, Janssen, RJ, van Gerven, MAJ, Steens, SC, Góraj, B, Koopmans, PP, Kessels, RPC, 2016. Resting-state subcortical functional connectivity in HIV-infected patients on long-term cART. Brain Imaging Behav. doi:10.1007/s11682-016-9632-4
  14. van Gerven, MAJ (2016). A primer on encoding models in sensory neuroscience. J Math Psychol. In Press.
  15. van de Nieuwenhuijzen, ME, van den Borne, E, Jensen, O, van Gerven, MAJ (2016). Spatiotemporal dynamics of cortical representations during and after stimulus presentation. Frontiers in Systems Neuroscience. DOI: 10.3389/fnsys.2016.00042.
  16. Dijkstra, N, van de Nieuwenhuijzen, ME, van Gerven, MAJ (2016). The spatiotemporal dynamics of binocular rivalry: evidence for increased top-down flow prior to a perceptual switch. Neuroscience of Consciousness. DOI: http://dx.doi.org/10.1093/nc/niw003.
  17. Jiang, H, Popov, T, Jylänki, P, Bi, K, Yao, Z, Lu, Q, Jensen, O, van Gerven, MAJ (2016). Predictability of depression severity based on posterior alpha oscillations. Clinical Neurophysiology, 127(4): 2108–2114.
  18. Güçlü, U, van Gerven, MAJ (2015). Increasingly complex representations of natural movies across the dorsal stream are shared between subjects. Neuroimage. In Press.
  19. Hinne, M, Janssen, RJ, Heskes, T, van Gerven, MAJ (2015). Bayesian estimation of conditional independence graphs improves functional connectivity estimates. PLoS Comp Biol, 11(11): e1004534.
  20. Lüttke, C, Ekman, M, van Gerven, MAJ, de Lange, FP (2015). Preference for audiovisual speech congruency in superior temporal cortex. J Cog Neurosci, 28(1), 1-7.
  21. Janssen, RJ, Jylänki, P, Kessels, RPC, van Gerven, MAJ (2015). Probabilistic model-based functional parcellation reveals a robust, fine-grained subdivision of the striatum. NeuroImage, 119, 398–405.
  22. Güçlü, U, van Gerven, MAJ (2015). Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. J. Neurosci., 35(27):10005-10014.
  23. Jiang, H, Bahramisharif, A, van Gerven, MAJ, Jensen, O (2015). Measuring directionality between neuronal oscillations of different frequencies. Neuroimage, 118:359-367.
  24. Hinne, M, Ekman, M, Janssen, R, Heskes, T, van Gerven, MAJ (2015). Probabilistic clustering of the human connectome identifies communities and hubs. PLoS ONE, 10(1): e0117179.
  25. Jiang, H, van Gerven, MAJ, Jensen, O. Modality-specific alpha modulations facilitate long-term memory encoding in the presence of distracters. J Cogn Neurosci. 2015. 27(3):583-592
  26. Simanova, I, van Gerven, MAJ, Oostenveld, R, Hagoort, P. Predicting the semantic category of internally generated words from neuromagnetic recordings. J Cogn Neurosci. 2015. 27(1):35-45.
  27. Schoenmakers, S, Güçlü, U, van Gerven, MAJ, Heskes, T. Gaussian mixture models and semantic gating improve reconstructions from human brain activity. Frontiers in Computational Neuroscience. 2014. 8(173).
  28. Lopez-Gordo, MA, Sanchez Morillo, D, van Gerven, MAJ. Spreading codes enables the blind estimation of the hemodynamic response with short-events sequences. Int J Neur Syst. 2014. DOI: 10.1142/S012906571450035X
  29. Hinne, M, Lenkoski, A, Heskes, T, van Gerven, MAJ. Efficient sampling of Gaussian graphical models using conditional Bayes factors. Stat. 2014; DOI:10.1002/sta4.66
  30. Janssen, RJ, Hinne, M, Heskes, T, van Gerven, MAJ. Quantifying uncertainty in brain network measures using Bayesian connectomics. Frontiers in Computational Neuroscience. 2014; DOI:10.3389/fncom.2014.00126
  31. Güçlü, U and van Gerven, MAJ. Unsupervised feature learning improves prediction of human brain activity in response to natural images. PLoS Comput Biol. 2014; DOI: 10.1371/journal.pcbi.1003724.
  32. Simanova, I, Hagoort, P, Oostenveld, R, van Gerven, MAJ. Modality-independent decoding of semantic information from the human brain. Cereb Cortex. 2014; 24:426-434.
  33. Hinne M, Ambrogioni L, Janssen R, Heskes T, van Gerven, MAJ. Structurally-informed Bayesian functional connectivity analysis. NeuroImage. 2014; 86:294-305.
  34. Bahramisharif, A, van Gerven, MAJ, Aarnoutse, E, Mercier, M, Schwartz, T, Foxe, J, Ramsey, N, Jensen, O. Propagating neocortical gamma bursts are coordinated by traveling alpha waves. The Journal of Neuroscience. 2013; 33(48):18849-18854.
  35. Roijendijk, L, Farquhar, J, van Gerven, MAJ, Jensen, O, Gielen, S. Exploring the impact of target eccentricity and task difficulty on covert visual spatial attention and its implications for brain computer interfacing. PLoS ONE. 2013; 8(12):e80489.
  36. Niazi, AM, van den Broek, PLC, Klanke, S, Barth, M, Poel, M, van Gerven, MAJ. Online decoding of object-based attention using real-time fMRI. European Journal of Neuroscience. 2013; 39(2):319-329.
  37. Kok P, Brouwer GJ, van Gerven MAJ, de Lange FP. Prior expectations bias sensory representations in visual cortex. The Journal of Neuroscience. 2013; 33(41):16275-16284.
  38. van de Nieuwenhuijzen, ME, Backus, AR, Bahramisharif, A, Doeller, CF, Jensen, O, van Gerven, MAJ. MEG-based decoding of the spatiotemporal dynamics of visual category perception. Neuroimage. 2013; 83:1063-1073.
  39. Schoenmakers, S, Barth, M, Heskes, T, van Gerven, MAJ. Linear reconstruction of perceived images from human brain activity. Neuroimage. 2013; 83:951-961.
  40. Vidaurre, D, van Gerven MAJ, Bielza, C, Larrañaga, P, Heskes, T. Bayesian sparse partial least squares. Neural Computation. 2013; 25(12):3318-3339.
  41. Brouwer, A-M, Reuderink, B, Vincent, J, van Gerven, MAJ, van Erp, JBF. Distinguishing between target and nontarget fixations in a visual search task using fixation-related potentials. Journal of Vision. 2013; 13(3).
  42. Geuze, J, van Gerven, MAJ, Farquhar, J, Desain P. Detecting semantic priming at the single-trial level. PLoS ONE. 2013; 8(4): e60377
  43. van Gerven, MAJ, Maris, E, Sperling, M, Sharan, A, Litt, B, Anderson, C, Baltuch, G, Jacobs, J. Decoding the memorization of individual stimuli with direct human brain recordings. Neuroimage. 2012; 70:223-232.
  44. Hinne, M, Heskes, T, Beckmann, CF, van Gerven, MAJ. Bayesian inference of structural brain networks. Neuroimage. 2012; 66:543-552.
  45. van Gerven, MAJ, Chao ZC, Heskes, T. On the decoding of intracranial data using sparse orthonormalized partial least squares. J Neural Eng. 2012; 9(2):026017.
  46. Llera A, van Gerven MAJ, Gómez V, Kappen HJ. On the use of interaction error potentials for adaptive brain computer interfaces. Neural Networks. 2011; 24(10):1120-1127.
  47. Jensen O, Oostenveld R, Klanke S, Hadjipapas A, Okazaki Y, van Gerven MAJ. Using brain-computer interfaces and brain-state dependent stimulation as a tool in cognitive neuroscience. Frontiers in Psychology. 2011;2.
  48. van Gerven MAJ, Kok P, de Lange FP, Heskes T. Dynamic decoding of ongoing perception. Neuroimage. 2011; 57:950–957.
  49. Treder MS, Bahramisharif A, Schmidt NM, van Gerven MAJ, Blankertz B. Brain-computer interfacing using modulations of alpha activity induced by covert shifts of attention. J. NeuroEngineering and Rehabil. 2011; 8(24).
  50. Bahramisharif A, Heskes T, Jensen O, van Gerven MAJ. Lateralized responses during covert attention are modulated by target eccentricity. Neurosci. Lett. 2011; 491(1):35-39.
  51. Simanova I, van Gerven MAJ, Oostenveld R, Hagoort P. Identifying object categories from event-related EEG: toward decoding of conceptual representations. PLoS ONE. 2010; 5(12):e14465.
  52. van Gerven MAJ, de Lange FP, Heskes T. Neural decoding with hierarchical generative models. Neural Comput. 2010; 22(12):3127-3142
  53. van Gerven MAJ, Cseke B, de Lange FP, Heskes T. Efficient Bayesian multivariate fMRI analysis using a sparsifying spatio-temporal prior. Neuroimage. 2010; 50(1):150-161.
  54. Bahramisharif A, van Gerven MAJ, Heskes T, Jensen O. Covert attention allows for continuous control of brain-computer interfaces. Eur. J. Neurosci. 2010; 31(8):1501-1508.
  55. van Gerven MAJ, Bahramisharif A, Heskes T, Jensen O. Selecting features for BCI control based on a covert spatial attention paradigm. Neural Netw. 2009; 22(9):1271-1277.
  56. van Gerven MAJ, Farquhar J, Schaefer R, Vlek R, Geuze J, Nijholt A, et al. The brain-computer interface cycle. J Neural Eng. 2009; 6(4):041001.
  57. van Gerven MAJ, Hesse C, Jensen O, Heskes T. Interpreting single trial data using groupwise regularisation. Neuroimage. 2009; 46(3):665-676.
  58. van Gerven MAJ, Jensen O. Attention modulations of posterior alpha as a control signal for two-dimensional brain-computer interfaces. J. Neurosci. Methods. 2009; 179(1):78-84.
  59. Willems D, Niels R, van Gerven MAJ, Vuurpijl L. Iconic and multi-stroke gesture recognition. Pattern Recognit. 2009;42(12):3303-3312.
  60. van Gerven MAJ, Taal BG, Lucas PJF. Dynamic Bayesian networks as prognostic models for clinical patient management. J Biomed Inform. 2008; 41(4):515-529.
  61. van Gerven MAJ, Lucas PJF, van der Weide, TP. A generic qualitative characterization of independence of causal influence. Internat J Approx Reas. 2008; 48(1):214-136.
  62. van Gerven MAJ, Jurgelenaite R, Taal BG, Heskes T, Lucas PJF. Predicting carcinoid heart disease with the noisy-threshold classifier. Artif Intell Med. 2007; 40(1):4555.
  63. van Gerven MAJ, Díez FJ, Taal BG, Lucas PJF. Selecting treatment strategies with dynamic limited-memory influence diagrams. Artif Intell Med. 2007; 40(3):171-186.

Selected conference and workshop proceedings

  1. Güçlütürk, Y., Güçlü, U., Seeliger, K., Bosch, S., Van Lier, R., van Gerven, M., 2017. Deep adversarial neural decoding. NIPS 2017. 1-12.
  2. Berezutskaya, J., Freudenburg, Z., Ramsey, N., Güçlü , U., van Gerven, M.A.J. Modeling brain responses to perceived speech with LSTM networks, BENELEARN, 2017.
  3. Ambrogioni, L., Hinne, M., van Gerven, M.A.J., Maris, E., 2017. GP CaKe: Effective brain connectivity with causal kernels. arXiv. NIPS 2017, 1–10.
  4. Escalante, H. J., Guyon, I., Escalera, S., Jr, J. J., Ayache, S., Viegas, E., … van Lier, R. (2017). Design of an explainable machine learning challenge for video interviews, IJCNN, 3688–3695.
  5. Grant, E., Kohli, P, van Gerven, M.A.J. Deep disentangled representations for volumetric reconstruction ECCV 2016. Lecture Notes in Computer Science, 9915, 266-279, 2016.
  6. Güçlütürk, Y., Güçlü, U., van Lier, R., van Gerven, M.A.J. (2016). Convolutional sketch inversion. In: Hua G., Jégou H. (eds) Computer Vision – ECCV 2016 Workshops. ECCV 2016. Lecture Notes in Computer Science, vol 9913. Springer, Cham
  7. Güçlü, U., Thielen, J., Hanke, M., & van Gerven, M.A.J. Brains on beats. NIPS. 2016
  8. Güçlütürk, Y., Güçlü, U., van Gerven, M.A.J., van Lier, R., 2016. Deep impression: Audiovisual deep residual networks for multimodal apparent personality trait recognition. ECCV 2016. arXiv:1609.05119 [cs.CV]. 2016.
  9. Grant, E., Sahm, S., Zabihi, M, van Gerven, M.A.J.
    Predicting and visualizing psychological attributions with a deep neural network. 23rd International Conference on Pattern Recognition. 2016.
  10. Güçlü, U, Knechten, M. and van Gerven, MAJ. A two-stage approach to estimating voxel-specific encoding models improves prediction of hemodynamic responses to natural images. In: Neuroinformatics 2014. Frontiers in Neuroinformatics. 2014.
  11. Schoenmakers, S, van Gerven, MAJ, Heskes, T. Gaussian mixture models improve fMRI-based image reconstruction. In: IEEE Proceedings of Pattern Recognition in Neuroimaging. 2014
  12. van de Nieuwenhuijzen, M, Jensen, O, van Gerven, MAJ. Reading what’s on your mind: Decoding images of different categories from working memory maintenance. In: Biomag. 2014.
  13. Hinne, M, Heskes, T, van Gerven, MAJ. Structural connectivity estimation via Bayesian data fusion. In: Human Brain Mapping. 2013.
  14. Güçlü, U and van Gerven, MAJ. Unsupervised learning of invariant features for encoding fMRI responses to natural images. In: Human Brain Mapping. 2013.
  15. Hinne, M, Eckman, M, Heskes, T, van Gerven, MAJ. Learning parcellated brain networks with an infinite relational model prior. In: Bayesian Non-parametrics 9. 2013
  16. Güçlü, U and van Gerven, MAJ. Unsupervised learning of features for Bayesian decoding in functional magnetic resonance imaging. In: BENELEARN 2013.
  17. Bahramisharif, A, van Gerven, MAJ, Jensen, O. Occipital alpha power and covert visual spatial attention in 2D. In: Biomag2012.
  18. van de Nieuwenhuijzen, M, Backus, A, Bahramisharif, A, Doeller, C, Jensen, O, van Gerven, MAJ. Classifying perceived natural images from MEG data using multivariate methods. In: Biomag2012.
  19. Backus, AR, van Gerven, MAJ, Jensen, O, Doeller, C. Category-specific changes in resting-state brain connectivity on multiple timescales following a sequence encoding task. In: Amsterdam Memory Slam 2012.
  20. Backus AR, Meeuwissen EB, Jensen O, van Gerven MAJ. Investigating the spatiotemporal dynamics of long-term memory retrieval using multivariate pattern analyses on magnetoencephalography Data. In: NIPS 2011 workshop on Machine Learning and Interpretation in Neuroimaging.
  21. Wouters HJP, van Gerven MAJ, Heskes T, Treder MS, Bahramisharif A. Covert attention as a paradigm for subject-independent brain-computer interfacing. In: NIPS 2011 workshop on Machine Learning and Interpretation in Neuroimaging.
  22. Bahramisharif A, van Gerven MAJ, Schoffelen J-M, Ghahramani Z, Heskes T. The dynamic beamformer. In: NIPS 2011 workshop on Machine Learning and Interpretation in Neuroimaging.
  23. van Gerven MAJ, Maris E, Heskes T. A Markov random field approach to neural encoding and decoding. In: ICANN 2011. 2011.
  24. van Gerven MAJ, de Lange FP, Heskes T. A hierarchical generative model for percept reconstruction. In: Human Brain Mapping. 2010.
  25. van Gerven MAJ, Simanova I. Concept classification with Bayesian multi-task learning. In: NAACL-HLT workshop on Computational Neurolinguistics. 2010.
  26. van Gerven MAJ, Heskes T. Sparse orthonormalized partial least squares. In: BNAIC. 2010.
  27. Simanova I, van Gerven MAJ, Oostenveld R, Hagoort P. Identifying object categories from event-related EEG: Toward decoding of conceptual representations. In: Human Brain Mapping. 2010.
  28. van Gerven MAJ, Bahramisharif A, Jensen O. Modulations in alpha activity by covert attention: a new 2D control signal for BCI. In: 8th Dutch Endo-Neuro-Psycho Meeting. Doorwerth, the Netherlands: 2009.
  29. Bahramisharif A, van Gerven MAJ, Heskes T. Exploring the impact of alternative feature representations on BCI classification. In: European Symposium on Artificial Neural Networks. 2009.
  30. Birlutiu A, Dijkstra TMH, van Gerven MAJ, Heskes T. Does the immune system have an influence on malaria parasite gene expression? In: 5th Netherlands Institute for Systems Biology Symposium. 2009.
  31. van Gerven MAJ, Cseke B, Oostenveld R, Heskes T. Bayesian source localization with the multivariate Laplace prior. In: Bengio Y, Schuurmans D, Lafferty J, Williams CKI, Culotta A, editors. Neural Information Processing Systems 23. 2009. p. 1901-1909.
  32. van Gerven MAJ, Takashima A, Heskes T. Selecting and identifying regions of interest using groupwise regularization. In: NIPS Workshop on New Directions in Statistical Learning for Meaningful and Reproducible fMRI Analysis. 2008.
  33. van Gerven MAJ. Tensor decompositions for probabilistic classification. In: Intelligent Data Analysis in bioMedicine and Pharmacology (IDAMAP) 2007. 2007.

Technical reports

  1. Solin, A., Jylänki, P., Kauramäki, J., Heskes, T., van Gerven, M.A.J., Särkkä, S. (2016). Regularizing solutions to the MEG inverse problem using space-time separable covariance functions. arXiv:1604.04931 [stat.AP].
  2. Güçlü, U., & van Gerven, M.A.J. (2015). Semantic vector space models predict neural responses to complex visual stimuli. arXiv:1510.04738. 2015
  3. van Gerven M.A.J., Heskes T. (2008) L1/Lp regularization of differences. Radboud University Nijmegen
  4. Heskes T, van Gerven M.A.J. (2008) Stability conditions for L1/Lp regularization. Nijmegen, The Netherlands: Radboud University Nijmegen
  5. van Gerven M.A.J. (2007) Approximate inference in graphical models using tensor decompositions. Radboud University Nijmegen
  6. van Gerven M.A.J. (2006) Efficient Bayesian inference by factorizing conditional probability distributions. Nijmegen, The Netherlands: Radboud University
  7. van Gerven M.A.J, Taal BG. (2006) Structure and parameters of a Bayesian network for carcinoid prognosis. Nijmegen, The Netherlands: Radboud University Nijmegen
  • image

    Cognitive Neuroscience

    Uncovering computational principles of human brain function

    We are interested in the brain mechanisms that allow humans to solve complex problems that require closing of the perception-action cycle. We design cognitively challenging tasks and have human participants execute them to investigate their behavioral and/or neural responses using sophisticated analysis techniques developed in the group. These techniques are based on Bayesian, neural network and reinforcement learning approaches.

  • image

    Artificial Intelligence

    Building machines that think like humans

    Next to understanding the empirical basis of complex problem solving, we are interested in the theoretical underpinnings of adaptive behaviour. Specifically, we ask whether computational models that are rooted in AI can provide an account of the learning, inference and control problems that are solved by the human brain. To address this question, we develop new learning algorithms and simulate adaptive behaviour in artificial agents.

  • image

    Human-Machine Interaction

    Creating new interfaces between humans and machines

    Understanding how the human brain solves cognitively challenging tasks is facilitated by the development of computational models that solve these tasks. We train computational models that learn to solve the task at hand and interrogate their internal states to find out how the network accomplishes this. We can then relate these internal states to the behaviour and neural signatures that human participants produce when solving the same task. By combining computational modelling and human behaviour and neural data in this way, we can elucidate the mechanisms that underlie human cognition.

  • image

    Code

    Some code

    Code description

  • image

    Data

    Some data

    Data description

  • image

    Internships

    Master students are welcome to join us on various projects in AI and neuroscience.

    Projects focus on improving our understanding of natural intelligence. This can take the form of creating new intelligent algorithms or empirical studies in cognitive (neuro)science. We also support more applied projects in the domain of e.g. health, security and robotics.

    We welcome motivated students with an exact mindset and programming experience. In case you are interested just send us an e-mail.

  • image

    Neural Networks

    B.Sc. Artificial Intelligence (AI-B2)

    During the lectures, the formal concepts underlying modern neural networks will be developed, including deep neural networks and recurrent neural networks. Also, various classic neural network models will be discussed like the (multi-layer) Perceptron, Hopfield networks and Boltzmann machines. During the practicals, students will get to immers themselves in the theoretical and practical aspects of neural networks. Students will get to implement various models using Python, a programming language which they will learn to use during the course.

    More details.

  • image

    Neural Information Processing Systems

    M.Sc. Artificial Intelligence (MA-AI)

    A main objective of artificial intelligence is to build machines whose cognitive abilities match (or surpass) those of humans. This is also referred to as strong AI. One way to achieve this goal is by developing cognitive architectures that implement the algorithms used by our own brains. This success of such an approach relies on a continuous interplay between AI and neuroscience.

    In this course, we will explore how computational models, particularly neural networks, can yield new insights about the mechanisms that give rise to natural intelligence and provide us with the tools to model cognitive processes in artificial systems.

    The course consists of different components:

    • During the lectures, students will get acquainted with the formal aspects and practical development of computational models of cognitive processes. They will learn about the current state of research concerning the modeling and understanding of natural intelligence.
    • Students will present key papers on the state of the art in class themselves.
    • During the practical sessions, students will learn to write computer programs related to specific topics discussed in class. To this end, the Python programming language will be used.
    • In the final part of the course, students will formulate their own research project. The outcome of the research project should be a working computational model accompanied by a NIPS style conference paper that provides original insights about cognitive processing in artificial and/or biological agents.

    More details.