Jonathan Deaton

TL;DR: This work shows the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain, and shows that this problem appears in a wide variety of practical ML pipelines.

TL;DR: In this paper, a multi-instance contrastive learning (MICLe) method was proposed to construct more informative positive pairs for self-supervised learning in medical image classification and achieved an improvement of 6.7% in top-1 accuracy and 1.1% in mean AUC on dermatology and chest X-ray classification.

TL;DR: A phage identification tool that uses supervised learning to classify metagenomic contigs as phage or non-phage on the basis of tetranucleotide frequencies, and the performance of phage genome prediction and taxonomic classification is analyzed using PhaMers.

TL;DR: It is found the performance of few-show learning methods does not reach that of conventional class imbalance techniques, but combining the two approaches using a novel ensemble improves model performance, especially for rare classes.

TL;DR: A computational approach that uses supervised learning to classify metagenomic contigs as phage or non‐phage as well as assigning phage taxonomy based on tetranucleotide frequencies is described, demonstrating the value of combining viral sequence identification with mini‐metagenomic experimental methods to understand the microbial ecosystem.