Results 191 to 200 of about 28,952 (292)

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

STAID: A Self‐Refining Deep Learning Framework for Spatial Cell‐Type Deconvolution with Biologically Informed Modeling

Advanced Science, EarlyView.
STAID is a unified deep learning framework that couples iterative pseudo‐spot refinement with neural network training through a feedback loop and exploits gene co‐expression information to model higher‐order interactions, achieving accurate and robust cell‐type deconvolution in spatial transcriptomics.
Jixin Liu, Shuli Sun, Zhengliang Lv, Xinyu Liu, Yihua Wang, Bingqiang Liu   +5 more
wiley   +1 more source

A dual enhanced stochastic gradient descent method with dynamic momentum and step size adaptation for improved optimization performance. [PDF]

Sci Rep
Mokhtar MA, Fathy M, Dahab YA, Sayed EA.
europepmc   +1 more source

Field‐Free Spin‐Splitting‐Torque Driven Stochastic Neuron Mimicking the Neuromorphic Imagination for High‐Performance Recognition

Advanced Science, EarlyView.
The human brain's imagination, which enables autonomous driving hazard avoidance by completing missing visual information, relies on Gaussian‐stochastic neuron. We report the altermagnetic RuO2 spintronic neurons integrating field‐free switching and intrinsic Gaussian stochasticity, building an all‐spin ANN for high‐quality image repairing and high ...
Junwei Zeng, Baoshan Cui, Xi Guo, Jiahao Liu, Xiaoyu Feng, Liang Fang, Li Xi, Xiaolong Fan, Xiaoxi Liu, Yang Guo   +9 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

Averaging Projected Stochastic Gradient Descent for Large Scale Square Problem

, 2012
The least squares problem is one of the most important regression problems in statistics and machine learning. In this paper, we present an Averaging Projection Stochastic Gradient Descent (APSGD) algorithm to solve the large-scale least squares problem.
Mu, Yang
core  

Diffusion‐Based Generative Model With Scaffold‐Hopping Strategy Yields Highly Potent Bioactive Molecules

Advanced Science, EarlyView.
SMarT‐Diff introduces a multi‐objective generative paradigm that integrates scaffold hopping with structure‐aware scoring to enable controlled exploration beyond the training distribution. The framework consistently balances drug‐likeness, synthesizes accessibility and bioactivity, yielding chemically diverse candidates with enhanced properties.
Yuwei Yang, Xiaoqing Gong, Shukai Gu, Jing Li, Bo Liu, Yanan Tian, Qianqian Zhang, Xiaojun Yao, Huanxiang Liu   +8 more
wiley   +1 more source

Efficient high-resolution refinement in cryo-EM with stochastic gradient descent. [PDF]

Acta Crystallogr D Struct Biol
Toader B, Brubaker MA, Lederman RR.
europepmc   +1 more source

Scaled stochastic gradient descent for low-rank matrix completion

, 2016
© 2016 IEEE. The paper looks at a scaled variant of the stochastic gradient descent algorithm for the matrix completion problem. Specifically, we propose a novel matrix-scaling of the partial derivatives that acts as an efficient preconditioning for the ...
Sepulchre, R, Mishra, B, ,
core  

Inhibitory Decay and Supercritical Brain Dynamics During Sleep Deprivation

Advanced Science, EarlyView.
Sleep deprivation progressively shifts human brain dynamics from near‐critical toward supercritical states, as revealed by neuronal avalanche analysis of resting‐state fMRI. These changes track subjective sleep pressure rather than vigilance lapses and show marked network heterogeneity. A circuit model suggests that reduced inhibitory efficacy provides
Dai Zhang, Liqin Zhou, Rong Wang, Yuehua Han, Zhentao Zuo, Yanghua Tian, Ke Zhou   +6 more
wiley   +1 more source