Iterative semi-supervised learning: helping the user to find the right records
, 2004 Chris Drummond
openalex +1 more source
Advanced Theory and Simulations, EarlyView.Three charge assignment approaches (one quantum chemistry method‐based, the other two machine‐learning (ML) model‐based) are employed to investigate acetylene separation performances of experimental covalent‐organic frameworks. Partial Atomic Charge Predicter for Porous Materials based on Graph Convolutional Neural Network (PACMAN) ML model‐based ...
Hakan Demir, Ilknur Erucar
wiley +1 more source
A new method of semi-supervised learning classification based on multi-mode augmentation in small labeled sample environment. [PDF]
Sci RepLiu Y, Wen C.
europepmc +1 more source
Semi-supervised learning by search of optimal target vector
, 2007 Leonardo Angelini +3 more
openalex +1 more source
Advanced Theory and Simulations, EarlyView.This study introduces a deep Q‐learning framework for semi‐transparent organic solar cells, combining AI and the Transfer Matrix Method to balance transparency/efficiency. Targeting PBDB‐T:ITIC‐based layers with asymmetric DMD contacts, the algorithm optimizes thickness/material properties, achieving 48.97% AVT and sustained photocurrent.
Erman Cokduygulular +2 more
wiley +1 more source
Improving drug-target affinity prediction by adaptive self-supervised learning. [PDF]
PeerJ Comput SciYe Q, Sun Y.
europepmc +1 more source
Substrate‐Restricted Asymmetric Evolution of Solid‐State Nanopores
Advanced Theory and Simulations, EarlyView.Standalone nanopores can either expand or shrink based on the nucleation mechanism. A substrate‐restricted asymmetric pore dynamics are uncovered ‐ top expansion and bottom shrinkage, with minimum aperture reduced and forming a conical geometry, driven by molecular migration along an energy potential gradient within nanopores.
Hongshuai Liu +4 more
wiley +1 more source
Enhancing 3D dopamine transporter imaging as a biomarker for Parkinson's disease via self-supervised learning with diffusion models. [PDF]
Cell Rep MedWon J +13 more
europepmc +1 more source
CRCFound: A Colorectal Cancer CT Image Foundation Model Based on Self‐Supervised Learning
Advanced Science, EarlyView.CRCFound is a self‐supervised learning‐based CT image foundation model for colorectal cancer (CRC). Pretrained on 5137 unlabeled CRC CT images, it learns universal feature representations, enabling efficient adaptation to various clinical tasks. The model demonstrates outstanding performance and generalization across multiple diagnostic and prognosis ...
Jing Yang +13 more
wiley +1 more source
Graph-RPI: predicting RNA-protein interactions via graph autoencoder and self-supervised learning strategies. [PDF]
Brief BioinformGuan J +7 more
europepmc +1 more source