21 June (Wednesday)

22 June (Thursday)

23 June (Friday)

 Breakfast  7.30am at Wilson Lounge    8am at Wilson Lounge  8am at Wilson Lounge

8

 

Nilearn

 

Causality

Opening (at 8:30)

 

9

Keynote: Janaina Mourao-Miranda (remote)

Keynote: Randy McIntosh

10

Site Effects in FC

Oral session 1: Graphs and Distances

Oral session 3: Statistical Methods

11

12

Lunch

Townhall (during lunch)

1

Nilearn (continued)

Deep Learning

Oral session 2: EEG/MEG

Oral session 4: Applications

2

3

Poster session

Closing (end at 3:30)

4

 

5

Keynote: Irina Rish

Keynote: Rajeev Raizada

 

 

Opening reception: Wilson Lounge

Gala dinner: Canyon Creek Chop House, Front Street

 



Coffee Breaks, Breakfast, and Lunch

Breakfast, lunch, and coffee breaks are provided each day, and included in the registration fee. All will be held at the venue, in the Wilson Lounge (in the building opposite to the William Too auditorium). Breakfast will begin at 7:30 on Wednesday, and at 8:00 on Thursday and Friday. Morning and afternoon (10am and 3pm) coffee breaks will be approximately 15 minutes each.


Accepted Papers and Abstracts

Accepted papers and abstracts are listed here.


Student Awards

The student travel awards were kindly sponsored by the Max Planck Institute for Intelligent Systems (Germany).
Best Student Paper Award: Brahim Belaoucha; Control & Signal Processing; Athena Project Team; Inria Sophia Antipolis - Méditerranée (France)
Best Student Poster Award: Carol Jew; Raizada Lab; Department of Brain & Cognitive Sciences; University of Rochester (USA)


Keynote Speakers

Randy McIntosh
Randy McIntosh
Title: Bridging Clinical and Cognitive Neuroscience With Large-Scale Computational Modeling
Abstract: A vast amount of data has been acquired at each of these scales, contributing to a growing knowledge of brain function at the level of the individual neuron, neural ensembles, or large-scale networks. A fuller understanding of brain function remains elusive, however, because no single technology currently exists to simultaneously acquire data across all spatial and temporal scales. As a result, little is known about the dependencies of one scale on the next and tasks such as directly linking cellular mechanisms with specific cognitive functions or dysfunctions remain a great challenge. TheVirtualBrain (TVB, thevirtualbrain.org) neuroinformatics platform begins to address this gap by building a unifying theoretical framework to quantify the relations between scales. TVB makes use of empirical data as the foundation for large-scale computer simulations of brain dynamics. Models based on individual subjects EEG and fMRI data have identified common local biophysical and global network properties that fuse modalities. The direct link to empirical data enables a personalization of clinical models, opening a potential use for diagnosis and prognosis. We have used TVB to identify biophysical parameters estimating local excitation/inhibition balance that predict therapeutic outcome in stroke patient. TVB models for epileptic patients can help confirm identification of seizure focus and accurately simulate seizure propagation. TVB thus acts as a much needed “computational microscope” that allows the direct inference of neurobiological mechanisms underlying human brain function in both health and disease.

Dr. Randy McIntosh is vice-president of Research at Baycrest and director of Baycrest's Rotman Research Institute, and Professor of Psychology at the University of Toronto. Dr. McIntosh is a pioneer in the study of how different parts of the brain work together to bring about the wide range of human mental operations. He is leading a team of international scientists on the development of The Virtual Brain (thevirtualbrain.org), which has the potential to revolutionize how clinicians assess and treat various brain disorders, including cognitive impairment caused by stroke and Alzheimer’s disease. The computerized model will deliver the first real, usable and open simulation of the human brain. For researchers, surgeons, neuroscientists and therapists, The Virtual Brain promises improved patient outcomes by letting clinicians simulate cognitive interventions – right from a Web browser.


Janaina Mourao-Miranda
Janaina Mourao-Miranda
Title: Machine learning and neuroimaging in mental health
Abstract: Over the last decade machine learning techniques have been successfully applied to clinical neuroimaging data leading to a growing body of research focused on diagnosis and prognosis of mental health disorders. With the technological advances enabling acquisition of large volumes of patient data, new machine learning models that can combine information from neuroimaging techniques with complementary knowledge from clinical assessments and general patient information have the potential to identify reliable biological markers and improve patient characterization in psychiatry. In this talk I will review some examples of how machine learning techniques have been applied to investigate clinical problems in neuroimaging, discuss the main challenges faced by these applications and outline potential alternatives to overcome them.

Dr. Janaina Mourao-Miranda is a Professorial Research Associate and Wellcome Trust Senior Fellow at the Computer Science Department, UCL and at the Max Planck UCL Centre for Computational Psychiatry and Ageing Research. Her research focuses on developing and applying machine-learning models to investigate complex relationships between neuroimaging data and multidimensional descriptions of mental health disorders. More specifically, her research group investigates the following questions: can we learn about underlying brain mechanisms of mental disorders from these relationships? Can we better stratify patient groups based on these relationships? Can we combine information from clinical assessments with different neuroimaging modalities to build better diagnostic and prognostic models of mental health disorders?

Note: Janaina will be presenting remotely, rather than attending PRNI in person.


Rajeev Raizada
Rajeev Raizada
Title: How computational models of words and sentences can reveal meaning in the brain
Abstract: Linguistic meaning is full of structure, and in order to understand language the human brain must somehow represent that. My colleagues and I have explored how the brain achieves that, using computational models of the meanings of words, and also of words combined into phrases and sentences. In particular, we have been tackling the following questions: How are the brain's representations of meaning structured, and how do they relate to models of meaning from Computer Science and Cognitive Psychology? How do neural representations of individual words relate to the representations of multiple words that are combined together into phrases and sentences? This work recently led to the first study to perform fMRI decoding of sentences. I will describe that work, and outline some of the many unsolved problems that remain.

Dr. Rajeev Raizada is an Assistant Professor in the Department of Brain & Cognitive Sciences at the University of Rochester, and also a member of the university's Center of Excellence in Data Science. His research uses pattern recognition algorithms to investigate the structure of neural representations in the human brain, concentrating especially on visual object recognition and linguistic meaning. More information about the research in his lab can be found at http://raizadalab.org and on Twitter at @RaizadaLab.




Irina Rish
Title: Learning About the Brain and Brain-Inspired Learning
Abstract: Quantifying mental states and identifying "statistical biomarkers" of mental disorders from neuroimaging data is an exciting and rapidly growing research area at the intersection of neuroscience and machine learning. Given the focus on gaining better insights about the brain functioning, rather than just learning accurate "black-box" predictors, interpretability and reproducibility of learned models become particularly important in this field. We will discuss promises and limitations of machine learning in neuroimaging, and lessons learned from applying various approaches, from sparse models to deep neural nets, to a wide range of neuroimaging studies involving pain perception, schizophrenia, cocaine addiction and other mental disorders. Moreover, we will also go "beyond the scanner" and discuss some recent work on inferring mental states from relatively cheap and easily collected data, such as speech and wearable sensors, with applications ranging from clinical settings ("computational psychiatry") to everyday life ("augmented human"). Finally, besides the above “AI to Brain” direction, we will also discuss the “Brain to AI”, namely, borrowing ideas from neuroscience to improve machine learning, with specific focus on adult neurogenesis and online model adaptation in representation learning.

Dr. Irina Rish is a researcher at the AI Foundations department of IBM T.J. Watson Research Center. She received MS in Applied Mathematics from Moscow Gubkin Institute, Russia, and PhD in Computer Science from the University of California, Irvine. Her areas of expertise include artificial intelligence and machine learning, with a particular focus on probabilistic graphical models, sparsity and compressed sensing, active learning, and their applications to various domains, ranging from diagnosis and performance management of distributed computer systems ("autonomic computing") to predictive modeling and statistical biomarker discovery in neuroimaging and other biological data. Irina has published over 60 research papers, several book chapters, two edited books, and a monograph on Sparse Modeling, taught several tutorials and organized multiple workshops at machine-learning conferences, including NIPS, ICML and ECML. She holds 24 patents and several IBM awards. As an adjunct professor at the EE Department of Columbia University, she taught several advanced graduate courses on statistical learning and sparse signal modeling.