We develop methods, benchmarks, and training systems that turn expert data into frontier AI

Constructing large, labeled training datasets for segmentation models is an expensive and labor-intensive process. This is a common challenge in machine learning, addressed by methods that require few or no labeled data points such as few-shot learning (FSL) and weakly-supervised learning (WS). Such techniques, however, have limitations when applied to image segmentation—FSL methods often produce noisy results and are strongly…

We focus on the problem of training deep image classification models for a small number of extremely rare categories. In this common, real-world scenario, almost all images belong to the background category in the dataset. We find that state-of-the-art approaches for training on imbalanced datasets do not produce accurate deep models in this regime. Our solution is to split the…

Widespread adoption of electronic health records (EHRs) has fueled the development of using machine learning to build prediction models for various clinical outcomes. However, this process is often constrained by having a relatively small number of patient records for training the model. We demonstrate that using patient representation schemes inspired from techniques in natural language processing can increase the accuracy…

This work demonstrates how organizational resources, in the form of aggregate statistics, knowledge bases, and existing services can be used to connect new and existing data modalities.

Electrophysiological signals exhibit both periodic and aperiodic properties. Periodic oscillations have been linked to numerous physiological, cognitive, behavioral and disease states. Emerging evidence demonstrates that the aperiodic component has putative physiological interpretations and that it dynamically changes with age, task demands and cognitive states. Electrophysiological neural activity is typically analyzed using canonically defined frequency bands, without consideration of the aperiodic…

Introducing FlyingSquid, a weak supervision framework that runs orders of magnitude faster than previous weak supervision approaches and requires fewer assumptions

This paper proposes cross-modal data programming (XMDP) for machine learning (ML) in medicine.

This paper provides a series of results studying how performance scales with changes in source coverage, source accuracy, and the Lipschitzness of label distributions in the embedding space, and compare this rate to standard weak supervision.

Presenting Trove, a framework for weakly supervised entity classification using medical ontologies and expert-generated rules.