Workshop: Machine learning for functional brain imaging

Machine learning for functional brain imaging

Symposium and Workshop

19th -20th of January 2017

 

! Below, you'll find the detailed PROGRAM and in some cases a PDF of the slides from the talk.

! Bottom of page, you'll find links to recommended further reading from the speakers.

 

PROGRAM ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::

 

Symposium – Thursday, 19th of January

Venue: Nobel forum, Nobels väg 1, Karolinska Institutet, Solna

 

 

8.30 – 8.40:

Welcome!

Daniel Lundqvist and Rita Almeida, Karolinska Institutet

8.40 – 9.10:

Introduction to machine learning in brain imaging

Alexandre Gramfort, Télécom ParisTech, Université Paris-Saclay

You'll find Alex's slides here.

9.10 – 10.00:

Dynamics of visual cognition: A spatio-temporally resolved and algorithmically explicit account

Radoslaw Martin Cichy, Free University Berlin

You'll find Radek's slides here.

 

10.00 – 10.30: Coffee break

 

10.30 – 10.50:

Using machine learning to detect onset of conscious visual experience

Lau Møller Andersen‎, NatMEG, Karolinska Institutet

You'll find Lau's slides here.

10.50 – 11.10:

Machine learning with dynamic functional connectivity and temporal networks

William Thompson‎, Karolinska Institutet

11.10 – 12.00:

Machine learning in real-time MEG: Challenges and applications

Lauri Parkkonen, Aalto University School of Science

 

Lunch break (lunch not provided)

 

13.20 – 14.10:

What does brain decoding teach us about human cognition? –

John-Dylan Wolfgang Haynes, Bernstein Center for Computational Neuroscience,

Charité - Universitätsmedizin Berlin

14.10 – 14.30:

A cortex-like network approach to large-scale analysis of brain imaging data with focus on EEG

Pawel Herman, Kungliga Tekniska Högskolan

14.30 – 14.50: Decoding cortical representations of the physical self

Malin Björnsdotter, Linköping University

 

14.50 – 15.20: Coffee break

 

15.20 – 16.10:

Modeling human brain function with artificial neural networks –

Marcel van Gerven, Donders Institute for Brain, Cognition and Behaviour

You'll find Marcel's slides here.

16.10 – 16.30:

Cortical representations of motor sequences

Diana Müssgens‎, Karolinska Institutet

16.30 – 16.50:

Brain-To-Brain Hyperclassification Reveals Shared Neural Signatures for Sensory and Vicarious Somatosensation

Fanny Lachat‎, NatMEG, Karolinska Institutet

 

17.00 – 18.00: Mingle

 

Workshop – Friday, 20th of January

 

9.00 – 12.00: Venue: Room 221, Nobels väg 9, Karolinska Institutet, Solna

MEG tutorial

Alexandre Gramfort, Télécom ParisTech, Université Paris-Saclay

Tutor: Lau Møller Andersen‎, NatMEG, Karolinska Institutet

 

9.00 – 12.00: Venue: Room Marie, Tomtebodavägen 18b, Karolinska Institutet, Solna

fMRI tutorial – Decoding and machine learning on brain MRI with nilearn,

Gaël Pascal Varoquaux, Inria, Parietal

Tutors: Jonathan Berrebi and Rita Almeida, Karolinska Institutet

 

Lunch break (lunch not provided)

 

13.00 – 15.00:

fMRI tutorial – continuation

13.00 – 15.00:

MEG tutorial – continuation

 

 

LEARN MORE ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::

 

Radek Cichy

  1. Resolving human object recognition in space and time.
  2. Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence.

 

Lau Andersen

  1. Occipital MEG Activity in the Early Time Range (<300 ms) Predicts Graded Changes in Perceptual Consciousness

 

William Thompson

  1. From static to temporal network theory - applications to functional brain connectivity
  2. Bursty properties revealed in large-scale brain networks with a point-based method for dynamic functional connectivity

 

John-Dylan Haynes

  1. A Primer on Pattern-Based Approaches to fMRI: Principles, Pitfalls, and Perspectives
  2. Decoding visual consciousness from human brain signals.

 

Marcel van Gerven

  1. A primer on encoding models in sensory neuroscience
  2. Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
  3. Deep Impression: Audiovisual Deep Residual Networks for Multimodal Apparent Personality Trait Recognition

 

Gaël Varoquax

  1. Machine learning for neuroimaging with scikit-learn
  2. How machine learning is shaping cognitive neuroimaging
  3. Assessing and tuning brain decoders: Cross-validation, caveats, and guidelines