Results 61 to 70 of about 11,467,392 (329)
Onception: Active Learning with Expert Advice for Real World Machine Translation
Computational Linguistics, 2023 Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate.
Vânia Mendonça +3 more
doaj +1 more source
Microbiome‐blood–brain barrier interactions in aging — mechanisms and therapeutic potential
FEBS Letters, EarlyView.Aging reshapes the gut microbiome (↓SCFA‐producing commensals; ↑pro‐inflammatory outputs), shifting circulating metabolites (↓SCFAs; ↑LPS, ↑TMAO, ↑PAA) that act at the BBB to increase nonspecific transcytosis, alter transport, and promote astrocyte reactivity, heightening brain vulnerability.
Daniel Cuervo‐Zanatta +3 more
wiley +1 more source
Automated discovery of a robust interatomic potential for aluminum
Nature Communications, 2021 The accuracy of a machine-learned potential is limited by the quality and diversity of the training dataset. Here the authors propose an active learning approach to automatically construct general purpose machine-learning potentials here demonstrated for
Justin S. Smith +10 more
doaj +1 more source
Materials & Design, 2022 The simultaneous optimization of competing properties is a challenge of machine learning based materials design. We proposed a domain knowledge constrained active learning loop for the design of high entropy alloys with optimized strength and ductility ...
Hongchao Li +5 more
doaj +1 more source
Active Learning Approaches to Enhancing Neural Machine Translation: An Empirical Study
Findings, 2020 Active learning is an efficient approach for mitigating data dependency when training neural machine translation (NMT) models. In this paper, we explore new training frameworks by incorporating active learning into various techniques such as transfer ...
Yuekai Zhao +3 more
semanticscholar +1 more source
Structure‐forward targeting of claudins with synthetic binders
FEBS Letters, EarlyView.Claudins form the paracellular barriers between epithelial and endothelial tissues at tight junctions and are targets for molecular binders with the goal of modulating barrier permeability. Claudin‐binding molecules are relevant in drug delivery or in altering claudin interactions with disease‐causing proteins.
Alex J. Vecchio
wiley +1 more source
Scientific Reports, 2021 Machine learning is widely applied in drug discovery research to predict molecular properties and aid in the identification of active compounds. Herein, we introduce a new approach that uses model-internal information from compound activity predictions ...
Raquel Rodríguez-Pérez +1 more
doaj +1 more source
Machine learning-enabled forward prediction and inverse design of 4D-printed active plates
Nature CommunicationsShape transformations of active composites (ACs) depend on the spatial distribution of constituent materials. Voxel-level complex material distributions can be encoded by 3D printing, offering enormous freedom for possible shape-change 4D-printed ACs ...
Xiao-Hao Sun +8 more
semanticscholar +1 more source
Optimising Selective Sampling for Bootstrapping Named Entity Recognition [PDF]
, 2005 Training a statistical named entity recognition system in a new domain requires costly manual annotation of large quantities of in-domain data. Active learning promises to reduce the annotation cost by selecting only highly informative data points.
Hachey, Benjamin Clayton +5 more
core
Towards a Theory of Representation Learning for Reinforcement Learning
, 2021 Presented online via Bluejeans Events on September 15, 2021 at 12:15 p.m.Alekh Agarwal is a researcher who works on theoretical foundations of machine learning, spanning many areas including large-scale and distributed optimization, high-dimensional ...
Agarwal, Alekh
core