L. Estève will give a talk about continuous integration in scikit-learn at a LoOPS workshop on March 27th. More details at http://www.reseau-loops.github.io/journee_2017_03_IntegrationContinue.html.
We are pleased to announce the new 0.14 release of MNE-Python. As usual this release comes with new features, bug fixes, and many improvements to usability, visualization, and documentation.
More information here: http://martinos.org/mne/stable/whats_new.html#whats-new
Some of our best members will part to the MNE-Python coding sprint in New York next week:
Go go team !
If you’ve completed your PhD thesis less than one year ago and want to spend one year to 18 months in a collaboration between Parietal and Poldrack’s lab at Stanford, this is a great opportunity:
Deadline on March 31st !
Gael will give a talk at the next Neurospin unsupervised decoding meeting on 21/02/2017 – 9h45-11h00, room 2032
Abstract: Recently, I have become convinced that cross-validation on a hundred or
less samples is not a reliable measure of predictive accuracy. In
addition, techniques generally used to estimate its error or test for
significant prediction are severely optimistic.
I would like to present you very simple evidence of this unreliability,
which it intrinsic to the sample sizes that we are working with. It is a
simple sampling-noise problem that cannot be alleviated without increasing
the number of samples.
I want to have a discussion about what this means for the field, and how
we should address this problem. I would like to invite critical thinking
about aspects of the practice that I might have overlooked and could make
it more robust.
I invite many people to come, so that we can convince ourselves of
whether or not there is a problem with the way we often work. Indeed, it
is troublesome for methods development as well as for neuroscience
Bertrand takes part to the table ronde “Big data & health” on January 28th at La Cité des Sciences, Paris.
A renewable (up to three years) post-doc project to chart the human brain at high resolution.
See more details here.
Andrés has successfully defended his PhD thesis “Ensembles of models in fMRI: stable learning in large-scale settings” on January 20th, in front of a committee comprising:
- Martin Lindquist
- Florent Krzakala
- Christophe Phillips
- Erwan le Pennec
- Bertrand Thirion
We have just released a first batch of >500 brain images on NeuroVault (http://neurovault.org/collections/2138/). These high-resolution images (1.5mm) represent activations of the 12 subjects of the IBC cohort for a first set of functional contrasts and are the first step toward a normative dataset that will be the basis of a brain atlas based on cognitive representations.