User profiles for Paroma Varma
Paroma VarmaGraduate Student, Stanford University Verified email at stanford.edu Cited by 2142 |
[HTML][HTML] Snuba: Automating weak supervision to label training data
As deep learning models are applied to increasingly diverse problems, a key bottleneck is
gathering enough high-quality training labels tailored to each task. Users therefore turn to …
gathering enough high-quality training labels tailored to each task. Users therefore turn to …
Parameterizing neural power spectra into periodic and aperiodic components
Electrophysiological signals exhibit both periodic and aperiodic properties. Periodic oscillations
have been linked to numerous physiological, cognitive, behavioral and disease states. …
have been linked to numerous physiological, cognitive, behavioral and disease states. …
[HTML][HTML] Training classifiers with natural language explanations
Training accurate classifiers requires many labels, but each label provides only limited
information (one bit for binary classification). In this work, we propose BabbleLabble, a framework …
information (one bit for binary classification). In this work, we propose BabbleLabble, a framework …
Scene graph prediction with limited labels
Visual knowledge bases such as Visual Genome power numerous applications in computer
vision, including visual question answering and captioning, but suffer from sparse, …
vision, including visual question answering and captioning, but suffer from sparse, …
Inferring generative model structure with static analysis
Obtaining enough labeled data to robustly train complex discriminative models is a major
bottleneck in the machine learning pipeline. A popular solution is combining multiple sources …
bottleneck in the machine learning pipeline. A popular solution is combining multiple sources …
Parameterizing neural power spectra
Electrophysiological signals across species and recording scales exhibit both periodic and
aperiodic features. Periodic oscillations have been widely studied and linked to numerous …
aperiodic features. Periodic oscillations have been widely studied and linked to numerous …
[HTML][HTML] Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences
Biomedical repositories such as the UK Biobank provide increasing access to prospectively
collected cardiac imaging, however these data are unlabeled, which creates barriers to their …
collected cardiac imaging, however these data are unlabeled, which creates barriers to their …
Learning dependency structures for weak supervision models
Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent
weak supervision approaches combine labels from multiple noisy sources by estimating their …
weak supervision approaches combine labels from multiple noisy sources by estimating their …
Multi-resolution weak supervision for sequential data
Since manually labeling training data is slow and expensive, recent industrial and scientific
research efforts have turned to weaker or noisier forms of supervision sources. However, …
research efforts have turned to weaker or noisier forms of supervision sources. However, …
Nonlinear optimization algorithm for partially coherent phase retrieval and source recovery
We propose a new algorithm for recovering both complex field (phase and amplitude) and
source distribution (illumination spatial coherence) from a stack of intensity images captured …
source distribution (illumination spatial coherence) from a stack of intensity images captured …