Graph neural processes for molecules: an evaluation on docking scores and strategies to improve generalization.

Neural processes (NPs) are models for meta-learning which output uncertainty estimates. So far, most studies of NPs have focused on low-dimensional datasets of highly-correlated tasks. While these homogeneous datasets are useful for benchmarking, they may not be representative of realistic transfer learning.

Rural Curricular Guidelines Based on Practice Scope of Recent Residency Graduates Practicing in Small Communities.

Background And Objectives: The optimal curriculum for training family physicians for rural practice within a traditional urban-based residency is not defined. We used the scope of practice among recent family medicine graduates of residencies associated with Preparing the Personal Physician for Practice (P4), practicing in small communities, to identify rural curriculum components.

Methods: We surveyed graduates 18 months after residency between 2007 and 2014.

Gaussian Processes for Data-Efficient Learning in Robotics and Control.

Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system to learn controllers, which is a practical limitation in real systems, such as robots, where many interactions can be impractical and time consuming. To address this problem, current learning approaches typically require task-specific knowledge in form of expert demonstrations, realistic simulators, pre-shaped policies, or specific knowledge about the underlying dynamics.

South Dakota accidental childhood deaths, 2000-2007: what can we do?

Introduction: Unintentional injuries are the leading cause of death in children around the world and are an under-recognized public health problem in the United States.

Purpose: The purpose of this study was to highlight the nature of the problem in South Dakota and outline interventions that have been successful in reducing childhood injuries in other states.

Methods: This quantitative retrospective study examined mortality files in South Dakota for children birth to 19 years of age who died between January 1, 2000 to December 28, 2007.

Modeling and visualizing uncertainty in gene expression clusters using dirichlet process mixtures.

Although the use of clustering methods has rapidly become one of the standard computational approaches in the literature of microarray gene expression data, little attention has been paid to uncertainty in the results obtained. Dirichlet process mixture (DPM) models provide a nonparametric Bayesian alternative to the bootstrap approach to modeling uncertainty in gene expression clustering. Most previously published applications of Bayesian model-based clustering methods have been to short time series data.