Results 121 to 130 of about 38,090 (261)

Phase diagram and eigenvalue dynamics of stochastic gradient descent in multilayer neural networks

Machine Learning: Science and Technology
Hyperparameter tuning is one of the essential steps to guarantee the convergence of machine learning models. We argue that intuition about the optimal choice of hyperparameters for stochastic gradient descent can be obtained by studying a neural network ...
Chanju Park, Biagio Lucini, Gert Aarts
doaj   +1 more source

Flexoelectricity in Photoconversion: Fundamentals, Materials, and Outlooks

Advanced Science, EarlyView.
Mechanical bending of a flexible cantilever induces a strain gradient in the photoactive material. The resulting flexoelectric field couples with photovoltaic and photoconductive effects, modulating charge generation, separation, and collection. A comparative analysis of oxide perovskites, halide perovskites, and two‐dimensional materials is presented,
Xiang Huang, Feng Li, Rongkun Zheng
wiley   +1 more source

From Label‐Free Multiphoton Imaging to Pathological Reports: A Vision‐Language Breast Cancer Margin Pathological Diagnosis System

Advanced Science, EarlyView.
MarginPath is a novel vision‐language system that automates breast cancer margin assessment using a single label‐free multiphoton microscopy image. By integrating tumor‐associated collagen signatures with virtual H&E imaging, it generates accurate margin heatmaps and comprehensive diagnostic reports.
Shu Wang, Jingze Su, Xiahui Han, Deyong Kang, Xiao Zhang, Fei Xu, Changzu Liu, Junlin Pan, Xingfu Wang, Qiaohui Zhan, Aimin Wang, Feng Huang, Heping Cheng, Wenxi Liu, Ruolan Lin, Jianxin Chen   +15 more
wiley   +1 more source

Detecting hidden states in stochastic dynamical systems

Physical Review Research
Inferring the number of states of a stochastic system from partial measurements is a fundamental problem in physics, for which methodological tools remain scarce. It is sometimes difficult to distinguish the stochastic dynamical states from measurements,
Rayan Succar, Alain Boldini, Maurizio Porfiri   +2 more
doaj   +1 more source

A Data‐Driven Inverse Design Methodology for Magnetic Soft Millirobots Navigating in Confined Spaces

Advanced Science, EarlyView.
A data‐efficient inverse design framework automates the optimization of magnetic soft millirobots for confined‐space navigation. Integrating a physics‐based Cosserat rod model with Bayesian optimization efficiently identifies high‐performance geometries.
Ziyu Ren, Hong Wang, Chak Wang Tse, Yi Zheng, Xi Chen, Wenqi Hu   +5 more
wiley   +1 more source

Herba Lysimachiae Polysaccharide‐Modified Selenium Nanoparticles Alleviate Oxidative Injury in Kidney Stones via TOMM22‐Regulated Mitophagy Activation

Advanced Science, EarlyView.
HLP‐SeNPs, a Lysimachia christinae polysaccharide‐modified selenium nanoparticle, treat kidney stones by downregulating TOMM22 expression, which reduces PINK1 translocation into mitochondria and promotes its retention on the outer mitochondrial membrane.
Junyi Yang, Guoruiyu Lyu, Wenlong Wan, Dongfeng Yuan, Jiabo Li, Yongqi Wang, Baokang Wang, Zhilong Ma, Yuanyuan Yang, Yang Xun, Xiao Yu   +10 more
wiley   +1 more source

Beyond Percolation: Graphene‐Enabled Network Reinforcement Enhances Thermal Transport in Paraffin Phase‐Change Composites

Advanced Science, EarlyView.
Expanded‐graphite/graphene‐nanoplatelet hybrids deliver a near‐order‐of‐magnitude thermal‐conductivity enhancement in paraffin phase‐change materials. A microCT‐informed 3D modeling framework resolves the percolating EG backbone and captures sub‐voxel GNP enrichment, quantitatively linking microstructure to heat flow and revealing a graphene‐enabled ...
Thomas Hoke, Jackson Hoke, Shucheng Guo, Brittany Chan, Xi Chen   +4 more
wiley   +1 more source

PhosSight: A Unified Deep Learning Framework Boosting and Accelerating Phosphoproteome Identification to Enable Biological Discoveries

Advanced Science, EarlyView.
PhosSight is a unified deep‐learning framework for phosphoproteome identification, featured by a phosphorylation‐aware detectability predictor. It improves identification sensitivity in DDA through deep re‐localization and rescoring, accelerates DIA searches by detectability‐guided spectral library pruning, and expands phosphoproteome coverage to ...
Ben Wang, Zhiyuan Cheng, Chengying She, Hongwei Zhao, Jiahui Zhang, Lin Lv, Zhihao Yan, Hongwen Zhu, Lizhuang Liu, Yan Fu, Xinpei Yi   +10 more
wiley   +1 more source

AI‐Designed Cyclic Peptides Enable Controllable Modulation of the CD28 Immune Checkpoint

Advanced Science, EarlyView.
AI‐designed cyclic peptides enable controllable modulation of the CD28 immune checkpoint through reversible disruption of CD28‐CD80/CD86 interactions. The lead peptide, CIP‐3, suppresses T‐cell activation without intrinsic agonist activity, demonstrates dose‐dependent efficacy in a murine colitis model, and attenuates inflammatory cytokine production ...
Katarzyna Kuncewicz, Saurabh Upadhyay, Renjie Zhu, Hongliang Duan, Moustafa T. Gabr   +4 more
wiley   +1 more source

KRT14 Drives Basal Muscle‐Invasive Bladder Cancer Progression and Lung Metastasis by Directly Binding to and Stabilizing IGF2BP1

Advanced Science, EarlyView.
We identified a Krt14+ Igf2bp1+ bladder cancer population linked to EMT. Mechanistically, KRT14 stabilizes and transports IGF2BP1 to invasive protrusions, initiating a positive feedback loop that drives metastasis and poor outcomes. ABSTRACT Basal‐type muscle‐invasive bladder cancer (BMIBC) is characterized by aggressive metastasis and poor prognosis ...
Shirui Huang, Zhihan Zhou, Qipeng Xie, Zheng Wang, Lijiong He, Yutong Liu, Lijuan Huang, Liuxian Ye, Limeng Hu, Baokun Li, Yang Wang, Xiaohui Hua, Xuelei Liu, Yunping Zhao, Jingxia Li, Jinfei Chen, Guiying Wang, Xian Shen, Wei Chen, Chuanshu Huang   +19 more
wiley   +1 more source