Elvio A. Blini
Elvio A. Blini
Home
Posts
Projects
Talks
Publications
Contact
Light
Dark
Automatic
dimensionality reduction
New article!
Pupillary manifolds: uncovering the latent geometrical structures behind phasic changes in pupil size.
We show that phasic changes in pupil size are inherently low-dimensional: they can be reconducted to a latent manifold that efficiently represents autonomic balance.
Elvio Blini
Nov 9, 2024
5 min read
Pupilla
,
pupil dilation
,
pupillometry
,
autonomic response
,
interoception
,
dimensionality reduction
,
pupillary manifold
,
pupillary fingerprints
,
machine learning
,
feature extraction
Project
Pupillary manifolds: uncovering the latent geometrical structures behind phasic changes in pupil size
Abstract The size of the pupils reflects directly the balance of different branches of the autonomic nervous system. This measure is inexpensive, non-invasive, and has provided invaluable insights on a wide range of mental processes, from attention to emotion and executive functions.
Elvio Blini
,
Roberto Arrighi
,
Giovanni Anobile
PDF
Cite
Project
DOI
New preprint!
Phasic changes in pupil size are strikingly low-dimensional!
In a new preprint, we show that very different tasks and processes map onto a very similar, low-dimensional latent space. We suggest that phasic changes in pupil size originate from a set of distinctive fingerprints that describe a pupillary manifold: a latent space that is highly constrained by the underlying physiological structures, i.e. the balance between different branches of the ANS.
Elvio Blini
May 24, 2024
3 min read
Pupilla
,
pupil dilation
,
pupillometry
,
autonomic response
,
interoception
,
dimensionality reduction
,
pupillary manifold
,
pupillary fingerprints
,
machine learning
,
feature extraction
Project
Assessment of machine learning pipelines for prediction of behavioral deficits from brain disconnectomes
Recent studies have shown that brain lesions following stroke can be probabilistically mapped onto disconnections of white matter tracts, and that the resulting “disconnectome” is predictive of the patient’s behavioral deficits.
Marco Zorzi
,
Michele de Filippo de Grazia
,
Elvio Blini
,
Alberto Testolin
PDF
Cite
Project
DOI
Cite
×