Examples are not enough, learn to criticize! criticism for interpretability
Example-based explanations are widely used in the effort to improve the interpretability of
highly complex distributions. However, prototypes alone are rarely sufficient to represent the …
highly complex distributions. However, prototypes alone are rarely sufficient to represent the …
[HTML][HTML] MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites
Quality control of MRI is essential for excluding problematic acquisitions and avoiding bias in
subsequent image processing and analysis. Visual inspection is subjective and impractical …
subsequent image processing and analysis. Visual inspection is subjective and impractical …
[PDF][PDF] The dynamics of functional brain networks: integrated network states during cognitive task performance
Higher brain function relies upon the ability to flexibly integrate information across specialized
communities of brain regions; however, it is unclear how this mechanism manifests over …
communities of brain regions; however, it is unclear how this mechanism manifests over …
[HTML][HTML] Long-term neural and physiological phenotyping of a single human
RA Poldrack, TO Laumann, O Koyejo, B Gregory… - Nature …, 2015 - nature.com
Psychiatric disorders are characterized by major fluctuations in psychological function over
the course of weeks and months, but the dynamic characteristics of brain function over this …
the course of weeks and months, but the dynamic characteristics of brain function over this …
Human cognition involves the dynamic integration of neural activity and neuromodulatory systems
The human brain integrates diverse cognitive processes into a coherent whole, shifting
fluidly as a function of changing environmental demands. Despite recent progress, the …
fluidly as a function of changing environmental demands. Despite recent progress, the …
[HTML][HTML] Toward open sharing of task-based fMRI data: the OpenfMRI project
The large-scale sharing of task-based functional neuroimaging data has the potential to
allow novel insights into the organization of mental function in the brain, but the field of …
allow novel insights into the organization of mental function in the brain, but the field of …
Generalized byzantine-tolerant sgd
We propose three new robust aggregation rules for distributed synchronous Stochastic
Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily …
Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily …
Fall of empires: Breaking byzantine-tolerant sgd by inner product manipulation
Recently, new defense techniques have been developed to tolerate Byzantine failures for
distributed machine learning. The Byzantine model captures workers that behave arbitrarily, …
distributed machine learning. The Byzantine model captures workers that behave arbitrarily, …
Consistent binary classification with generalized performance metrics
OO Koyejo, N Natarajan… - Advances in neural …, 2014 - proceedings.neurips.cc
Performance metrics for binary classification are designed to capture tradeoffs between four
fundamental population quantities: true positives, false positives, true negatives and false …
fundamental population quantities: true positives, false positives, true negatives and false …
Temporal metastates are associated with differential patterns of time-resolved connectivity, network topology, and attention
JM Shine, O Koyejo… - Proceedings of the …, 2016 - National Acad Sciences
Little is currently known about the coordination of neural activity over longitudinal timescales
and how these changes relate to behavior. To investigate this issue, we used resting-state …
and how these changes relate to behavior. To investigate this issue, we used resting-state …