We provide some recommendations on how to report machine learning-based research in order to improve transparency and reproducibility.
Volume 1 Issue 10, October 2021
News & Views
An efficient parallelization technique for tensor network contraction, developed by a careful balance between memory requirement and computational time, speeds up classical simulation of quantum computers.
Mobile-phone data reveal a cognitive strategy in human navigation and motivate the development of a new route planning model, with potential implications for traffic forecasting and transportation planning.
Finding a parameter that can accurately identify the order–disorder phase transition, especially for complex physical systems with high-dimensional configurational space, is a challenging task. Recent work proposes a machine learning approach to effectively tackle this challenge.
Quantum defects in two-dimensional materials offer promises for the next-generation quantum information technology. However, the rational design of these defects faces challenges, and thus, requires the development of advanced theoretical and computational models.
Using a statistical method for transient correlations, the waxing and waning in levels of population infection by SARS-CoV-2 are shown to respond to temperature and absolute humidity, across geographical locations and for different temporal and spatial resolutions.
An algorithmic approach is developed to analyze large-scale patient safety data and remove the confounders of reporting trajectory and drug inference. Such an approach can be effectively used to investigate demographic disparities of drug safety and to identify at-risk patients during a pandemic.
An analysis of GPS pedestrian traces shows that (1) people increasingly deviate from the shortest path when the distance between origin and destination increases and that (2) chosen paths are statistically different when origin and destination are swapped. Ultimately, this can explain the observed human attitude in selecting different paths upon return trips.
Neural network-based order parameter for phase transitions and its applications in high-entropy alloys
A variational autoencoder-based order parameter is proposed and demonstrated on various high-entropy alloys, providing a computational technique for understanding chemical ordering in alloys. Ultimately, this has the potential to facilitate the development of rational alloy design strategies.
A Poisson binomial-based statistical testing framework for comorbidity discovery across electronic health record datasets
A method for comorbidity discovery informed by each patient’s demographic and medical history is introduced. Statistics for 4,623,841 pairs of potentially comorbid medical terms are provided as a searchable web resource.