Multivariate analysis of neuroimaging data has gained ground very rapidly in the community over the past few years, leading to impressive results in cognitive and clinical neuroscience. Pattern recognition and machine learning conferences regularly feature a neuroimaging workshop, while neuroscientific meetings dedicate sessions to new approaches to neural data analysis. Thus, a rich two-way flow has been established between disciplines. It is the goal of the PRNI workshop series to continue facilitating exchange of ideas between scientific communities, with a particular interest in new approaches to the interpretation of neural data driven by new developments in pattern recognition and machine learning.

This year's 4th International Workshop on Pattern Recognition in Neuroimaging takes place at the Max Planck Institute for Intelligent Systems in Tübingen, a medieval university town in the south-west of Germany. Tübingen is conveniently located to Stuttgart airport (STR) and easily accessible by public transportation. PRNI 2014 is an official satellite meeting of the Annual Meeting of the Organization for Human Brain Mapping (OHBM).

PRNI 2014 solicits contributions of original four-page papers on pattern recognition in neuroimaging. Every submission will be reviewed by multiple experts and reviews will be double-blind. Accepted papers will be published in electronic format by Conference Publishing Services. They will be submitted for inclusion in IEEExplore and IEEE CS Digital Library online repositories, and submitted for indexing in IET INSPEC, EI Compendex (Elsevier), Thomson ISI, and others.


Registration open (May 7th)

Technical program online (May 4th)

Submission of camera-ready papers postponed to April 30th

Author notifications sent out (April 14th)

Author notifications postponed to April 14th

Important dates updated (March 21st)

Paper submission deadline extended to March 17th (March 2nd)

Submission website open (January 17th)

First call for papers sent out (December 10th)

Submission deadline is March 7th 2014

Section pull down arrow Breaker


PRNI 2014 will begin with a welcome barbecue on the 3rd of June at 6 pm, followed by a discussion on the future of the PRNI workshop series. Tutorials on the 4th will introduce attendees to current developments in machine learning for neuroimaging. June 5th and 6th will feature oral- as well as poster sessions on original research in the domain of pattern recognition for neuroimaging.

Keynote Speakers

John-Dylan Haynes

John-Dylan Haynes

Decoding and predicting intentions from brain signals

There has been a long debate on the existence of brain signals that precede the outcome of decisions, even before subjects believe they are consciously making up their mind. The framework of multivariate decoding provides a novel tool for investigating such choice-predictive information contained in neural signals leading up to a decision. New results show that the specific outcome of free choices between different plans can be interpreted from brain activity, not only after a decision has been made, but even several seconds before it is made. This suggests that a causal chain of events can occur outside subjective awareness even before a subject makes up his/her mind. An important future line of research would be to develop paradigms that allow feedback of real-time predictions of future decisions to reveal whether such decisions can still be reverted. This would shed light on how tight the causal link is between early predictive brain signals and subsequent decisions.


John-Dylan Haynes is Professor for Theory and Analysis of Large-Scale Brain Signals at the Bernstein Center for Computational Neuroscience and Director of Berlin Center for Advanced Neuroimaging (BCAN). His research focuses on decoding neural representations of mental states such as consciousness, intention or attention.

Klaus-Robert Müller

Klaus-Robert Müller

Multimodal imaging, non-stationarity and brain-computer interfacing

Learning to build universal decoders for brain-computer interfaces (BCIs) is a great challenge. Usually in multimodal imaging we consider the modes to be different types of imaging devices such as EEG, NIRS or fMRI. However, we can also interpret different subjects as imaging modalities to gain a zero training decoder from a data base of subjects. Even the same subject data from several experiments can be seen as instantiations of multiple modes. The talk will discuss recent multimodal analysis techniques such as SPoC. Furthermore we will discuss non-stationarities that often occur in neuroscience, e.g. between a subject's training and testing session in brain-computer interfacing. We show that such changes can be very similar between subjects, and thus can be reliably estimated using data from other users and utilized to construct an invariant feature space. These insights can be accumulated into a broader theoretical framework using beta divergences. We show that it can not only achieve a significant increase in performance, but also that the extracted change patterns allow for a neurophysiologically meaningful interpretation.


Klaus-Robert Müller is Professor for Computer Science at TU Berlin, Germany, and directing the Bernstein Focus on Neurotechnology Berlin. Since 2012 he is distinguished professor at Korea University within the WCU Program. His research interests are intelligent data analysis, machine learning, big data, signal processing and Brain Computer Interfaces. Recently he has expanded his interests towards the application of Machine Learning techniques in quantum physics and material sciences.

Russ Poldrack

Russ Poldrack

Large-scale decoding of neurocognitive organization

We are drowning in results from neuroimaging studies, but starving for an understanding of how these results inform the relation between psychological and brain function. I will describe an approach that uses large-scale multilabel decoding methods to better understand the latent brain functional organization that supports psychological functions, and to better understand the organization of psychological processes. This approach relies heavily on open databases, including the Neurosynth database of published literature and the OpenFMRI database of raw fMRI datasets, as well as leveraging ontologies of mental function such as the Cognitive Atlas. Together these tools provide us with a new way to conceptualize the organization of the mind as it is implemented in the brain.


Russ Poldrack is Professor of Psychology and Neuroscience and Director of the Imaging Research Center at the University of Texas at Austin, USA. His research interests focus on the intersection of decision making, learning and memory, and executive control, using fMRI and other imaging tools. His lab is also involved in the development of neuroinformatics resources for cognitive neuroscience, including the Cognitive Atlas and the OpenfMRI data sharing project.

Tuesday 3rd June:

Description From To:
Registration 18.00 21.00
Welcome barbecue 18.00 20.00
Discussion forum: The future of the PRNI workshop series 20.00 21.00


Tutorials will be held on June 4th. The two tutorials in the morning session will introduce fundamental concepts in machine learning and provide an introduction to current developments in pattern recognition for neuroimaging, respectively. In the afternoon, a practical session will allow participants to familiarize themselves with the use of a state-of-the-art machine-learning toolbox for analyzing neuroimaging data. The tutorial day will conclude with a first keynote.

Wednesday 4th June:

  • Welcome address
  • Learning theory (Ingo Steinwart)
  • Coffee break
  • Bayesian Modeling (Marcel van Gerven)
  • Lunch break
  • Practical session: : High performance computing in neuroimaging using BROCCOLI (Anders Eklund)
  • Coffee break
  • Keynote (Russ Poldrack)
  • Informal night out in Tübingen
Description From To:
Welcome address 9.00 9.15
Learning theory (Ingo Steinwart) 9.15 10.45
Coffee break 10.45 11.15
Bayesian Modeling (Marcel van Gerven) 11.15 12.45
Lunch break 12.45 14.00
Practical session: High performance computing in neuroimaging using BROCCOLI (Anders Eklund) 14.00 15.30
Coffee break 15.30 15.50
The Biomag 2014 Decoding Challenge: Brain Decoding Across Subjects (Paolo Avesani) 15.50 16.00
Keynote by Russ Poldrack 16.00 17.00
Informal night out in Tübingen 19:00 open end

Anders Eklund

Anders Eklund

High performance computing in neuroimaging using BROCCOLI

Analysis of functional magnetic resonance imaging (fMRI) data is becoming ever more computationally demanding as temporal and spatial resolutions improve, and large, publicly available data sets proliferate. Moreover, methodological improvements in the neuroimaging pipeline, such as non-linear spatial normalization, non-parametric permutation tests and Bayesian Markov Chain Monte Carlo approaches, can dramatically increase the computational burden. Despite these challenges, there do not yet exist any fMRI software packages which leverage inexpensive and powerful graphics processing units (GPUs) to perform these analyses. I will therefore give an introduction to general purpose computing on GPUS (GPGPU) and also present BROCCOLI, a free software package written in OpenCL (Open Computing Language). BROCCOLI can be used for parallel analysis of fMRI data on a large variety of hardware configurations and has, so far, been tested with an Intel CPU, an Nvidia GPU and an AMD GPU. These tests show that parallel processing of fMRI data can lead to significantly faster analysis pipelines. BROCCOLI running on a GPU can perform non-linear spatial normalization to a 1 mm brain template in 4-6 seconds, a speedup of about 200-500 times compared to FSL and AFNI, while still providing a satisfactory result. BROCCOLI can also run a second level permutation test with 10,000 permutations in about a minute, giving a speedup of 100-200 times compared to the function randomise in FSL. These non-parametric tests are generally more robust than their parametric counterparts, and can also enable more sophisticated analyses by estimating complicated null distributions. The new software is freely available under GNU GPL3 and can be downloaded from github (


Anders Eklund is a postdoctoral associate at the Virginia Tech Carilion Research Institute, Roanoke, USA. His research interests include image registration, machine learning, multivariate fMRI analysis, high performance computing and non-parametric statistics.

Ingo Steinwart

Marcel van Gerven

Bayesian Modeling

Bayesian statistics provides a rich and general framework for neural data analysis. In this tutorial I will introduce the mathematical underpinnings of Bayesian statistics and argue that Bayesian inversion of generative models provides a unifying way to perform data analysis in cognitive neuroscience. I will demonstrate this using two generative models which we have recently developed. The first model allows joint estimation of both structural and functional connectivity using multimodal datasets. The second model generates a connectivity-based parcellation of whole-brain networks and provides insight into the way brain regions are structurally coupled. I will end with a discussion on the pros and cons of Bayesian neural data analysis and provide an outlook on future work.


Marcel van Gerven is assistant professor at the Donders Institute for Brain, Cognition and Behaviour at Radboud University Nijmegen, The Netherlands. His research combines computational modeling which has its roots in computational neuroscience, Bayesian statistics and artificial intelligence with empirical work where brain activity is measured in naturalistic settings.

Ingo Steinwart

Ingo Steinwart

Learning theory

The last decade has witnessed a great success of machine learning techniques in various application areas. Many of these techniques are used to make statistical inference with the help of the given data, and the talk will describe the fundamentals of the theory behind them. In particular, we will present several criteria a good learning should satisfy and discuss some fundamental limitations of any learning algorithm. In the last part we will briefly demonstrate how these general findings can help to avoid misuse of support vector machines, which are one of the most popular learning algorithms for classification and regression problems.


Ingo Steinwart is full professor at the Institute for Stochastics and Applications, Department of Mathematics, University of Stuttgart, Germany. His research interests include statistical learning theory, Kernel-based learning methods (support vector machines) and Reproducing Kernel Hilbert spaces.

Oral and Poster Sessions

Thursday 5th June:

  • Welcome address
  • Oral session I:
    Multi-Subject Learning
  • Poster session I
    (including coffee)
  • Lunch break
  • Keynote by John-Dylan Haynes
  • Oral session II:
    Advances in M/EEG-Analysis
  • Coffee break
  • Oral session III:
    Advances in fMRI Analysis
  • Conference dinner
Description From To:
Welcome address 9.00 9.15
Oral session I: Multi-Subject Learning (Session Chair: Alexandre Gramfort) 9.15 11.15
Poster session I (including coffee) 11.15 13.00
Lunch break 13.00 14.15
Keynote by John-Dylan Haynes 14.15 15.15
Oral session II: Advances in M/EEG-Analysis (Session chair: Moritz Grosse-Wentrup) 15.15 16.40
Coffee break 16.40 17.00
Oral session III: Advances in fMRI Analysis (Session Chair: Dirk Bernhardt-Walther) 17.00 18.20
Conference dinner 19:00 open end

Oral Session I: Multi-Subject Learning Presenter Begin End
Welcome address Moritz Grosse-Wentrup (MPI) & Marcel van Gerven (Donders) 09.00 09.15
Full Bayesian multi-task learning for multi-output brain decoding and accommodating missing data (ID6) Andre Marquand (King's College London) 09.15 09.35
Classification of inter-subject fMRI data based on graph kernels (ID27) Sandro Vega Pons (Fondazione Bruno Kessler) 09.35 09.55
Multiple subject learning for inter-subject prediction (ID46) Sylvain Takerkart (CNRS - Aix Marseille Université) 09.55 10.15
Data-driven Multisubject Neuroimaging Analyses for Naturalistic Stimuli (ID60) Felix Biessmann (Amazon) 10.15 10.35
Multi-subject Bayesian Joint Detection and Estimation in fMRI (ID54) Solveig Badillo (CEA-INRIA) 10.35 10.55

Papers only accessible from within the institute's network.
Oral Session II: Advances in M/EEG-Analysis Presenter Begin End
Improved MEG/EEG source localization with reweighted mixed-norms (ID12) Daniel Strohmeier (TU Ilmenau) 15.15 15.35
Bayesian Correlated Component Analysis for Inference of Joint EEG Activation (ID42) Lars Kai Hansen (TU Denmark) 15.35 15.55
Mean shrinkage improves the classification of ERP signals by exploiting additional label information (ID51) Johannes Höhne (TU Berlin) 15.55 16.15
Parameter interpretation, regularization and source localization in multivariate linear models (ID10) Stefan Haufe (CUNY) 16.15 16.35

Oral Session III: Advances in fMRI-Analysis Presenter Begin End
Gaussian Mixture Models Improve fMRI-based Image Reconstruction (ID63) Sanne Schoenmakers (Radboud University) 17.00 17.20
Spatial Discriminant ICA for RS-fMRI characterisation (ID70) Alejandro Tabas (Bournemouth University) 17.20 17.40
Benchmarking solvers for TV- l1 least-squares and logistic regression in brain imaging (ID33) Elvis Dohmatob (INRIA) 17.40 18.00
Discriminative Subnetwork Mining for Multiple Thresholded Connectivity-Networks-Based Classification of MCI (ID38) Fei Fei (Nanjing University) 18.00 18.20

Poster Session I Presenter
Combining neuroanatomical and clinical data to improve individualized early diagnosis of schizophrenia in subjects at high familial risk (ID4) Eleni Zarogianni (University of Edinburgh)
Multimodal Neuroimaging in AD: Contributions of multi-voxel pattern analysis to the analysis of DTI and resting-state MRI (ID5) Carlo Rondinoni (University of Sao Paulo)
SVM aided detection of cognitive impairment in MS (ID8) Jeroen Van Schependom (VUB)
In Search of Biomarkers for Schizophrenia using Electroencephalography (ID9) Jorne Laton (VUB)
Unsupervised metrics of brain region significance for event-related fMRI intersession experiments (ID14) Loizos Markides (Imperial College London)
Sensor-level Maps with the Kernel Two-Sample Test (ID16) Emanuele Olivetti (NiLab Trento)
Improved Method for Automatic Cerebrovascular Labelling using Stochastic Tunnelling (ID17) Sahar Ghanavati (University of Toronto)
Fast Voxel Selection of fMRI Data Based on Smoothed l0 Norm (ID20) Zhiying Long (Beijing Normal University)
Functional Hyperalignment of Resting State fMRI Sessions Driven by Autonomic Activity (ID22) Vittorio Iacovella (FBK)
Decoding memory processing from electro-corticography in human posteromedial cortex (ID25) Jessica Schrouff (Stanford University)
Dynamic Connectivity Factorization: Interpretable decompositions of non-stationarity (ID31) Aapo Hyvarinen (University of Helsinki)
MVPA to enhance the study of rare cognitive events: an investigation of experimental PTSD (ID32) Katherine Niehaus (Oxford University)

Friday 6th June:

  • Keynote by Klaus-Robert Müller
  • Oral session IV:
    Brain Connectivity
  • Poster session II (including coffee)
  • Lunch break
  • Oral session V:
    Advances in sMRI Analysis
  • Coffee break
  • Oral session VI:
  • Awards ceremony and farewell
Description From To:
Keynote by Klaus-Robert Müller 9.00 10.00
Oral session IV: Brain Connectivity (Session Chair: Jonas Richiardi) 10.00 11.30
Poster session II (including coffee) 11.30 13.00
Lunch break 13.00 14.15
Oral session V: Advances in sMRI Analysis (Session Chair: Gabriele Lohmann) 14.15 15.40
Coffee break 15.40 16.00
Oral session VI: Applications (Session Chair: Gaël Varoquaux) 16.00 17.30
Awards ceremony and farewell 17.30 18.00

Oral Session IV: Brain Connectivity Presenter Begin End
Causal and anti-causal learning in pattern recognition for neuroimaging (ID34) Sebastian Weichwald (MPI-IS) 10.00 10.20
Joint Laplacian Diagonalization for Multi-Modal Brain Community Detection (ID85) Luca Dodero (IIT) 10.20 10.40
Correlation bundle statistics in fMRI data (ID21) Gabriele Lohman (MPI-KYB) 10.40 11.00
Hierarchical Topographic Factor Analysis (ID40) Jeremy Manning (Princeton) 11.00 11.20

Oral Session V: Advances in sMRI Analysis Presenter Begin End
Reduction of Confounding Effects with Voxel-wise Gaussian Process Regression in Structural MRI (ID68) Ahmed Abdulkadir (University of Freiburg) 14.15 14.35
Semi-supervised learning in MCI-to-AD conversion prediction - When is unlabeled data useful? (ID23) Jussi Tohka (TUT) 14.35 14.55
Nonparametric Bayesian Clustering of Structural Whole Brain Connectivity in Full Image Resolution (ID57) Karen Ambrosen (TUD) 14.55 15.15
Predictive support recovery with TV-Elastic Net penalty and logistic regression: an application to structural MRI (ID15) Édouard Duchesnay (CEA) 15.15 15.35

Oral Session VI: Applications Presenter Begin End
Multimodal diagnosis of epilepsy using conditional dependence and multiple imputation (ID66) Wesley Kerr (UCLA) 16.00 16.20
A perceptual-to-conceptual gradient of word coding along the ventral path (ID67) Valentina Borghesani (INSERM-CEA) 16.20 16.40
A study of spatial variation in fMRI brain networks via independent vector analysis: application to schizophrenia (ID73) Shruti Gopal (RIT) 16.40 17.00
Decoding perceptual thresholds from MEG/EEG (ID11) Alexandre Gramfort (TPT, CNRS, Neurospin-CEA) 17.00 17.20

Poster Session II Presenter
MEG Decoding Across Subjects (ID18) Emanuele Olivetti (NiLab Trento)
A MAP approach for Convex Non-negative Matrix Factorization in the Diagnosis of Brain Tumors (ID36) Albert Vilamala (UPC)
PET imaging analysis using a parcelation approach and multiple kernel classification (ID39) Fermin Segovia (University of Liège)
Improved Marked Point Process Priors for Single Neurite Tracing (ID41) Sreetama Basu (NUS)
Intensity normalisation for large-scale fMRI brain decoding (ID43) Loizos Markides (Imperial College)
A validation of a multi-spatial scale method for multivariate pattern analysis (ID47) Jessica Bulthé (KU Leuven)
Optimizing spatial filters for the extraction of envelope-coupled neural oscillations (ID50) Sven Dähne (TU-Berlin)
EEG Source Reconstruction using Sparse Basis Function Representations (ID52) Sofie Therese Hansen (TU Denmark)
Permutation Distributions of fMRI Classification do not behave in accord with Central Limit Theorem (ID56) Mohammed Al-Rawi (University of Coimbra)
Hierarchical Processing of Temporal Asymmetry in Human Auditory Cortex (ID71) Alejandro Tabas (Bournemouth University)
Single-trials ERPs predict correct answers to intelligence test questions (ID80) Siamac Fazli (Korea University)
Higher Dimensional fMRI Connectivity Dynamics Show Reduced Dynamism in Schizophrenia Patients (ID81) Robyn Miller (Mind Research Network)

Section pull down arrow Breaker

Author Information

Call for Papers

PRNI welcomes original papers on multivariate analysis of neuroimaging data, using invasive and non-invasive imaging modalities, including but not limited to the following topics:

  • Learning from neuroimaging data
    • Classification algorithms for brain-state decoding
    • Optimisation and regularisation
    • Bayesian analysis of neuroimaging data
    • Connectivity and causal inference
    • Combination of different data modalities
    • Efficient algorithms for large-scale data analysis
  • Interpretability of models and results
    • High-dimensional data visualisation
    • Multivariate and multiple hypothesis testing
    • Summarisation/presentation of inference results
  • Applications
    • Disease diagnosis and prognosis
    • Real-time decoding of brain states
    • Analysis of resting-state and task-based data

Submission Instructions

Authors should prepare full papers with a maximum length of 4 pages (double-column, IEEE style, PDF) for review, using this style sheet. Reviews will be double-blind, i.e. submissions have to be anonymized. This includes removing all information on the authors and their affiliations as well as citing own work in a passive voice. Non-anonymous submissions will be rejected without review. Each submission will be reviewed by a minimum of two reviewers. Manuscripts have to be submitted by March 17th, 2014, 11.59 pm (PST) via the submission website.

Accepted submissions will be assigned either to one of the oral- or one of the poster sessions, depending on the reviewers' evaluation. All accepted submissions will be included in the workshop proceedings. Every accepted submission has to be presented at the workshop by one of the paper's authors.

To submit the camera-ready PDF version of an accepted paper please proceed as follows:

  • Add the appropriate copyright notice at the left bottom of the first page of your document. There are three different copyright notices:
    • If all paper authors are employees of the U.S. government, use U.S. Government work not protected by U.S. copyright
    • If all authors are employed by a crown government (UK, Canada, and Australia), use 978-1-4799-4149-0/14/$31.00 ©2014 Crown
    • For all other papers, use 978-1-4799-4149-0/14/$31.00 ©2014 IEEE
    For papers generated with Latex the copyright notice can be incorporated by adding
    \IEEEpubid{\makebox[\columnwidth]{ PUT APPROPRIATE COPYRIGHT NOTICE HERE \hfill} \hspace{\columnsep}\makebox[\columnwidth]{ }}

    to the preamble of your document.
  • Remove page numbering from your document. In Latex, this can be done by adding \pagenumbering{gobble} to the preamble of your document.
  • Do not forget to remove all anonymisations in your camera-ready version, e.g. add authors again and replace anonymised references. Make sure your final PDF does not exceed the four-page limit.
  • Check whether your final PDF conforms to the IEEE guidelines via (Conference ID: 33559X). If you need help with the IEEE PDF express system, consult IEEE's online customer help.
  • Upload your final PDF via the CMT submission system by April 30th.
  • Also using the CMT system, fill out and upload the IEEE Copyright Form.
Papers that do not meet the above requirements or that are submitted later than April 30th will not be included in the proceedings.

Important dates:

  • Paper submission deadline (extended): 17th of March, 2014, 11.59 pm (Pacific Standard Time)
  • Acceptance notification: 14th of April, 2014
  • Camera-ready papers: 30th of April, 2014
  • Tutorials: 4th of June, 2014
  • Oral and poster sessions: June 5-6, 2014


A small number of papers will be selected for the Best Student Paper Award. To be eligible the paper's first author must be a student and must present the paper at the workshop. Awardees will receive a travel allowance. To apply for a best paper award, students should send an email to prni2014 (at) ), indicating the authors, title, and submission number of their paper. The results of the best student paper award will be announced at the awards ceremony on Friday June 6th.

The PRNI 2014 best student paper award goes to

Daniel Strohmeier

for the paper Improved MEG/EEG source localization with reweighted mixed-norms, co-authored with Jens Haueisen and Alexandre Gramfort.

Honourable mentions are awarded for the following two papers:

  • Elvis Dopgima Dohmatob, Alexandre Gramfort, Bertrand Thirion, and Gaëlle Varoquaux: Benchmarking solvers for TV-l1 least-squares and logistic regression in brain imaging.
  • Sylvain Takerkart and Liva Ralaivola: Multiple subject learning for inter-subject prediction.


Please read the following information carefully before registering.

Presenters of accepted papers: Authors of accepted papers who present their paper at the workshop must register as a PRIMARY AUTHOR by the early registration deadline (May 15th) to ensure inclusion of their paper in the proceedings. To register as a primary author, please select PRIMARY AUTHOR during the registration process and enter the paper ID. For each paper ID, only one author may register as a primary author. All other authors, who wish to attend the workshop, have to register as regular attendees. Multiple registrations as a primary author for the same paper ID will be canceled and a 15% cancellation fee will be charged. One primary author's registration covers up to two papers. Additional papers can be bought online during the registration process.

Non-presenting attendees: Presentation of an accepted paper is not a requirement for being able to register for and attend the workshop. Authors of accepted papers, who wish to attend the workshop but do not present their paper, and all others have to register as regular attendees during the registration process. Registrations of non-presenters in the PRIMARY AUTHOR category will be canceled and a 15% cancellation fee will be charged.

Reduced registration fees are available for IEEE members as well as for undergraduate and graduate students currently enrolled in a full-time study programme. For graduate students, student status is defined as up to the end of doctoral studies (thesis defense) at the time of registration. For IEEE student members, student status is validated online during the registration process. For non-IEEE student registrations, please send a proof of eligibility (e.g. a student ID or a brief statement by your superisor) to prni2014 (at) Attendees from countries with low-income or lower-middle-income economies, as classified by The World Bank, can apply for a reduced registration fee by sending an informal email to prni2014 (at)

The registration fee includes attendance of the tutorials and the workshop technical programme, a CD of the proceedings, lunch and coffee breaks on June 4-6, and the barbecue on the evening of June 3rd. Tickets for the conference dinner on June 5th are not included in the registration fee but can be bought online during the registration process.

Registrations may be cancelled with no fees up to the early registration deadline (May 15th). After this date a 15% cancellation fee will apply. No refunds will be given for cancellations after May 30th. No-shows at the workshop will not be refunded.

Approximate registration fees in Euros are as follows. Actual registration fees have to be paid in USD and may vary slightly.

Registration type Early registration (until May 15th) Late registration (after May 15th) On-site registration
IEEE student member 200€ 250€ 300€
IEEE member 200€ 250€ 300€
IEEE life member 200€ 250€ 300€
Non-IEEE student 200€ 250€ 300€
Regular 250€ 300€ 350€

To register, please click here.

Section pull down arrow Breaker



The workshop will be held on the campus of the Max Planck Institutes in Tübingen, Germany. Tübingen is a picturesque medieval university town, and can easily be reached by public transportation from Stuttgart airport (STR). Tübingen is furthermore well connected to the rest of Germany by railway.


We reserved a contingent of rooms in our guest house, hotels close to campus, and hotels in downtown Tübingen. To reserve a room please directly contact these hotels and cite PRNI.

Hotel Approximate price range Distance to campus Book until
Max Planck Guest House 40/75 Euros (single/double room) On campus FULL
Gästehaus Albblick 74 Euros (double room) 15 minute walk May 15th
Hotel Katharina 68-78/113 Euros (single/double room) 15 minute walk April 20th
Hotel Sand 67/90 Euros (single/double room) 25 minute walk May 5th
Hotel am Schloß 75-148 Euros Downtown Tübingen April 15th
Hotel Domizil 92/123 Euros (single/double room) Downtown Tübingen April 30th
Hotel Krone 99-179 Euros Downtown Tübingen April 30th


General Chair:

Moritz Grosse-Wentrup (MPI for Intelligent Systems, Tübingen, Germany)

Program Chairs:

Marcel van Gerven (Donders Institute for Brain, Cognition and Behaviour, Netherlands)
Nikolaos Koutsouleris (LMU Munich, Germany)

Steering committee:

Jonas Richiardi
Dimitri Van De Ville
Seong-Whan Lee
Yuki Kamitani
Janaina Mourao-Miranda
Christos Davatsikos
Gaël Varoquaux

Program committee:

John Ashburner
Dirk Bernhard-Walther
Cesar Caballero-Gaudes
Guillermo Cecchi
Kai-min Chang
Silvana Dellepiane
Peter Desain
Zafer Dogan
Christian Gaser
John-Dylan Haynes
Jeremy Hill
Fabien Lotte
Andre Marquand
Maarten Mennes
Thomas Nichols
Emanuele Olivetti
Irina Rish
Jane Rondina
Maria Rosa
Sylvain Takerkart
Bertrand Thirion
Diego Vidaurre
Mattias Villani
Shivakumar Viswanathan
Patrik Vuilleumier
Christian Wallraven
Thorsten Zander


PRNI 2014 is an official satellite meeting of the Organization for Human Brain Mapping (OHBM), technically co-sponsored by the IEEE Signal Processing Society, and an endorsed event of The Medical Image Computing and Computer Assisted Intervention Society (MICCAI). The workshop is generously supported by Brain Products GmbH.

IEEE Signal Processing Society Brain Products GmbH
Section pull down arrow Breaker


For all enquiries, please send an email to prni2014 (at) Please do not email the organizers individually.