Results 181 to 190 of about 1,338,397 (280)
Convergence of Hyperbolic Neural Networks Under Riemannian Stochastic Gradient Descent
We prove, under mild conditions, the convergence of a Riemannian gradient descent method for a hyperbolic neural network regression model, both in batch gradient descent and stochastic gradient descent.
Wang, Bao, Whiting, Wes, Xin, Jack
core +1 more source
Advances and Perspectives in Graphene‐Based Quantum Dots Enabled Neuromorphic Devices
Advanced Science, EarlyView.Graphene‐based QDs are zero‐dimensional carbon nanomaterials with pronounced quantum confinement and tunable electronic structures. Herein, we summarize their synthesis strategies and functionalization methods, and highlight their functional roles and operating mechanisms in devices, as well as recent advances in neuromorphic electronics. We anticipate
Yulin Zhen +9 more
wiley +1 more source
Nonparametric budgeted stochastic gradient descent
, 2016 One of the most challenging problems in kernel online learning is to bound the model size. Budgeted kernel online learning addresses this issue by bounding the model size to a predefined budget.
V Nguyen (9860309) +3 more
core
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
Polarization Dynamics in Ferroelectrics: Insights Enabled by Machine Learning Molecular Dynamics
Advanced Science, EarlyView.Machine learning molecular dynamics is presented as a route to capture polarization switching, domain wall kinetics, topological polar textures, and polar mechanical coupling beyond the limits of conventional atomistic methods. This Perspective surveys recent progress and identifies key methodological directions, including long‐range electrostatics ...
Dongyu Bai +3 more
wiley +1 more source
Neural networks are often employed in artificial intelligence because they are capable of learning patterns and approximating nonlinear functions from input data.
Pu Gong
core +1 more source
A Generative Neuro‐Symbolic AI for Protein Sequence Design
Advanced Science, EarlyView.We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne +12 more
wiley +1 more source
Enhancing Super‐Resolution Spatial Transcriptomics Data by Transfer Learning
Advanced Science, EarlyView.SpotZoomer employs a transfer‐learning‐based strategy to enhance the resolution of Visium data by leveraging available high‐resolution priors. The resulting super‐resolved maps enable sharper delineation of cell boundaries and more precise inference of cell–cell communication patterns that would otherwise remain obscured at native resolution.
Xiaoyu Li, Lihua Zhang, Wenwen Min
wiley +1 more source
Advanced Science, EarlyView.scTIDE identifies single‐cell tipping points by combining manifold‐based graph representations with optimal‐transport conditional flow matching, which preserves intrinsic topology and models distributional dynamics. It supports critical‐transition detection at individual‐cell resolution, prediction of unseen cells, and dimensionality reduction and ...
Jiayuan Zhong +6 more
wiley +1 more source
Advanced Science, EarlyView.An in situ‐grown BP‐CaO2 nanoplatform supplies coordinated Ca2+, endogenous phosphate, and oxidative stress to convert tumor calcification from a passive endpoint into an active immune‐remodeling process. Widespread hydroxyapatite deposition is visualized by CT, while multi‐omics reveals MCOLN2 as a calcium‐responsive mediator linking biomineralization
Long Liu +11 more
wiley +1 more source