Results 151 to 160 of about 368,237 (276)

Moral overfitting

Philosophical Studies
Abstract This is a paper about model-building and overfitting in normative ethics. Overfitting is recognized as a methodological error in modeling in the philosophy of science and scientific practice, but this concern has not been brought to bear on the practice of normative ethics. I first argue that moral inquiry shares similarities
openaire   +1 more source

From Cell‐Free Transcriptomes to Single‐Cell Landscapes: Biomarker Discovery and Originating Cell Alteration Analysis via Graph Matrix Factorization

Advanced Science, EarlyView.
CellFreeGMF traces plasma cfRNA to likely originating cell types by integrating single‐cell atlases with graph‐regularized matrix factorization. The method decomposes cfRNA profiles into sample–cell contributions to reconstruct pseudo single‐cell expression.
Wenxiang Zhang, Wenjing Zhang, Hang Wei, Shiyan Liu, Junliang Shang, Weijie Gong, Hanwen Cheng, Xiujuan Lei, Yuhui Kou, Baoguo Jiang   +9 more
wiley   +1 more source

Factors associated with work-related musculoskeletal disorders using machine learning approaches: a systematic review. [PDF]

Ann Occup Environ Med
Mohd Sallehhudin MI, Yasin SM, Isa MR, Razak TR, Mohamad Asraff MS, Che Rameli NA, Shahriman-Teruna MM, Mohamad Salleh MM, Mohamed Yusoff MZ, Ammar Khebir MH.   +9 more
europepmc   +1 more source

Decoding Structure‐Property Relationships in Anion Exchange Membranes via a Chemically Informed Dual‐Channel Graph Attention Network

Advanced Science, EarlyView.
SPARK decodes structure‐property relationships in anion exchange membranes (AEMs) via a chemically informed dual‐channel graph attention network (DEGAT) that explicitly captures microphase separation. It outputs five‐level grades for hydroxide conductivity and alkaline stability and highlights relevant key structural units, enabling robust pre ...
Wanting Chen, Ye Hu, Zijun Xiao, Deming Xia, Bo Pang, Xuemei Wu, Gaohong He   +6 more
wiley   +1 more source

Estimating seepage in heterogeneous earthfill dams on permeable foundations using explainable machine learning. [PDF]

Sci Rep
Sayed Ahmed MM, Khursheed MZ, Alshameri B, Hamed AK, Elshaarawy MK.   +4 more
europepmc   +1 more source

Faster and Durable: A Cell‐to‐System Validation of a Low‐Degradation Fast‐Charge Protocol for Li‐Ion Batteries

Advanced Science, EarlyView.
A physics‐based framework resolving graphite phase‐separation dynamics establishes a predictive, degradation‐aware fast‐charging methodology for commercial Li‐ion batteries. The resulting model‐informed protocol achieves 20%–80% state‐of‐charge in 14 min while matching the long‐term degradation of a commercial 25‐minute EV strategy.
Marco Lagnoni, Francesco Giuseppe Quilici, Davide Cademartori, Claudio Scarpelli, Uways Nurulain Mithoowani, Federica Barontini, Alessandro Ruvio, Monica Puccini, Giovanni Lutzemberger, Maria Paola Carpanese, Antonio Bertei   +10 more
wiley   +1 more source

Thyroid Nodule Detection and Classification on Small Datasets: An Ensemble Deep Learning Approach with Attention Mechanism and Focal Loss. [PDF]

Diagnostics (Basel)
Hung WC, Chang YK, Chang CM, Cheng PW, Lo WC, Cheng PC, Liao LJ.   +6 more
europepmc   +1 more source

Ultra‐Wide‐Field Noninvasive Imaging Through Scattering Media Via Physics‐Guided Deep Learning

Advanced Science, EarlyView.
We propose a physics‐guided adaptive dual‐domain learning method for ultra‐wide‐field noninvasive imaging through scattering media, namely UNI‐Net. Our method not only reduces the requirement for real experimental data by an order of magnitude but also enables clear imaging of complex scenes with an ultra‐large field of view, which is 164 times the OME
Lintao Peng, Mingwei He, Jeff Zhu, Sujit K. Sahoo, Liheng Bian, Cuong Dang   +5 more
wiley   +1 more source

Sufficient is better than optimal for training neural networks. [PDF]

Nat Commun
Babayan I, Aliahmadi H, van Anders G.
europepmc   +1 more source

Revisiting Target‐Aware de novo Molecular Generation with TarPass: Between Rational Design and Texas Sharpshooter

Advanced Science, EarlyView.
TarPass provides a rigorous benchmark for target‐aware de novo molecular generation by jointly evaluating protein‐ligand interactions, molecular plausibility, and drug‐likeness on 18 well‐studied targets. Results show that current models often fail to consistently surpass random baseline in target‐specific enrichment, while post hoc multi‐tier virtual ...
Rui Qin, Zijie Chen, Yurong Li, Meijing Fang, Longji Shen, Yilong Su, Odin Zhang, Qinghan Wang, Qun Su, Jike Wang, Tingjun Hou, Yu Kang   +11 more
wiley   +1 more source