Microsoft

Active Learning and Semi-supervised Learning for Speech Recognition: A Unified Framework using the Global Entropy Reduction Maximization Criterion

We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select a limited subset of ...
C&EN

Reactive Active Learning: An Efficient Approach for Training Machine Learning Interatomic Potentials for Reacting Systems

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Discovering chemical reaction pathways using quantum mechanics is impractical for many ...
Frontiers

A drop-out mechanism for active learning based on one-attribute heuristics

Active Learning (AL) leverages the principle that machine learning models can achieve high accuracy with fewer labeled samples by strategically selecting the most informative data points for training.
IEEE

SPOT: An Active Learning Algorithm for Efficient Deep Neural Network Training

Abstract: Recent advancements in deep neural networks heavily rely on large-scale labeled datasets. However, acquiring annotations for large datasets can be challenging due to annotation constraints.
Frontiers

Identification and validation of NETs-related biomarkers in active tuberculosis through bioinformatics analysis and machine learning algorithms

Department of Science and Education Division, Public Health Clinical Center of Chengdu, Chengdu, Sichuan, China Introduction: Diagnostic delays in tuberculosis (TB) threaten global control efforts, ...
BMJ

Development and validation of an interpretable machine learning model for predicting Philadelphia chromosome-positive acute lymphoblastic leukaemia using clinical and ...

2 State Key Laboratory of Trauma and Chemical Poisoning, Chongqing, China 3 Chongqing Key Laboratory of Hematology and Microenvironment, Chongqing, China Participants This study analysed 471 newly ...