Results 181 to 190 of about 142,362 (315)

Stochastic gradient descent

, 2018
David Wang, Andrew Murphy
openaire   +1 more source

Cogra: Concept-Drift-Aware Stochastic Gradient Descent for Time-Series Forecasting

, 2019
Kohei Miyaguchi, Hiroshi Kajino
openalex   +2 more sources

Identification and Characterization of an In Silico Designed Membrane‐Active Peptide with Antiviral Properties

Advanced Science, EarlyView.
An evolutionary molecular dynamics platform is used to design P1.6, a membrane‐active peptide that senses lipid packing defects in viral envelopes. P1.6 adopts a stabilized α‐helical structure upon membrane contact, disrupts virus‐like liposomes, and damages HIV‐1 particles.
Pascal von Maltitz, Niek van Hilten, Tatjana Weil, Thunchanok Thummaraj, Jeroen Methorst, Dennis Aschmann, Alexander Kros, Clarissa Read, Jasmina Gačanin, Herre Jelger Risselada, Jan Münch   +10 more
wiley   +1 more source

Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. [PDF]

J Stat Mech, 2020
Goldt S, Advani MS, Saxe AM, Krzakala F, Zdeborová L.   +4 more
europepmc   +1 more source

Personalized federated learning with exact stochastic gradient descent [PDF]

Sotirios Nikoloutsopoulos, Iordanis Koutsopoulos, Michalis K. Titsias   +2 more
openalex   +1 more source

scPER: A Rigorous Computational Approach to Determine Cellular Subtypes in Tumors Aligned With Cancer Phenotypes From Total RNA Sequencing

Advanced Science, EarlyView.
scPER presents an adversarial‐autoencoder framework that deconvolves bulk total RNA‐seq to quantify tumor‐microenvironment cell types and uncover phenotype‐linked subclusters. Across diverse benchmarks, scPER improves accuracy over existing tools.
Bingrui Li, Xiaobo Zhou, Raghu Kalluri
wiley   +1 more source

Active Force Dynamics in Red Blood Cells Under Non‐Invasive Optical Tweezers

Advanced Science, EarlyView.
A non‐invasive method combines low‐power optical tweezers with high‐speed microscopy to simultaneously monitor local membrane forces and displacements in single human red blood cells. This dual‐channel approach reveals a mechano‐dynamic signature that correlates the cell's metabolic state with its mechanical activity. This energetic framework serves as
Arnau Dorn, Clara Luque‐Rioja, Macarena Calero, Diego Herráez‐Aguilar, Francisco Monroy, Niccolò Caselli   +5 more
wiley   +1 more source

Dual module- wider and deeper stochastic gradient descent and dropout based dense neural network for movie recommendation. [PDF]

Sci Rep
C K R, K C S, C K S.
europepmc   +1 more source

Cancer‐Like Fragmentomic Characteristics of Somatic Variants in Cell‐Free DNA

Advanced Science, EarlyView.
We report that in non‐cancerous subjects, cell‐free (cfDNA) molecules harboring somatic variants exhibit cancer‐like fragmentomic characteristics associated with clonal hematopoiesis. Importantly, these somatic variant‐associated fragmentomic aberrations are more pronounced in cancer patients. Leveraging such somatic variant‐associated signals in cfDNA,
Zhenyu Zhang, Yunyun An, Mengqi Yang, Yuqi Pan, Xiaoyi Liu, Fanglei Gong, Huizhen Lin, Bianbian Tang, Yunxia Bai, Xin Zhao, Yu Zhao, Changzheng Du, Kun Sun   +12 more
wiley   +1 more source

A Communication-Efficient Stochastic Gradient Descent Algorithm for Distributed Nonconvex Optimization [PDF]

Antai Xie, Xinlei Yi, Xiaofan Wang, Ming Cao, Xiaoqiang Ren   +4 more
openalex   +1 more source