Results 51 to 60 of about 389,136 (225)

Variational Characterizations of Local Entropy and Heat Regularization in Deep Learning

open access: yes, 2019
The aim of this paper is to provide new theoretical and computational understanding on two loss regularizations employed in deep learning, known as local entropy and heat regularization.
Kaplan, Zach   +2 more
core   +1 more source

Hard‐Magnetic Soft Millirobots in Underactuated Systems

open access: yesAdvanced Robotics Research, EarlyView.
This review provides a comprehensive overview of hard‐magnetic soft millirobots in underactuated systems. It examines key advances in structural design, physics‐informed modeling, and control strategies, while highlighting the interplay among these domains.
Qiong Wang   +4 more
wiley   +1 more source

Learnable Diffusion Framework for Mouse V1 Neural Decoding

open access: yesAdvanced Science, EarlyView.
We introduce Sensorium‐Viz, a diffusion‐based framework for reconstructing high‐fidelity visual stimuli from mouse primary visual cortex activity. By integrating a novel spatial embedding module with a Diffusion Transformer (DiT) and a synthetic‐response augmentation strategy, our model outperforms state‐of‐the‐art fMRI‐based baselines, enabling robust
Kaiwen Deng   +2 more
wiley   +1 more source

Seeing the Error in My “Bayes”: A Quantified Degree of Belief Change Correlates with Children’s Pupillary Surprise Responses Following Explicit Predictions

open access: yesEntropy, 2023
Bayesian models allow us to investigate children’s belief revision alongside physiological states, such as “surprise”. Recent work finds that pupil dilation (or the “pupillary surprise response”) following expectancy violations is predictive of belief ...
Joseph Colantonio   +4 more
doaj   +1 more source

Atomic Defects in Layered Transition Metal Dichalcogenides for Sustainable Energy Storage and the Intelligent Trends in Data Analytics

open access: yesAdvanced Science, EarlyView.
This review comprehensively summarizes the atomic defects in TMDs for their applications in sustainable energy storage devices, along with the latest progress in ML methodologies for high‐throughput TEM data analysis, offering insights on how ML‐empowered microscopy facilitates bridging structure–property correlation and inspires knowledge for precise ...
Zheng Luo   +6 more
wiley   +1 more source

Fosl2 Regulates FSH‐Dependent Follicle Maturation Through Feedback Amplification of FSH/FSHR Signaling

open access: yesAdvanced Science, EarlyView.
This study identifies a FOSL2‐driven positive feedback loop that amplifies FSH/FSHR signaling. During FSH‐dependent follicle maturation, FSH induces Fosl2 expression via the cAMP‐PKA‐CREB cascade. FOSL2 in turn binds the promoters of Fshr and estrogen‐biosynthesis genes to enhance their transcription, thereby increasing Fshr mRNA level and amplifying ...
Hongru Shi   +13 more
wiley   +1 more source

Utilizing Amari-Alpha Divergence to Stabilize the Training of Generative Adversarial Networks

open access: yesEntropy, 2020
Generative Adversarial Nets (GANs) are one of the most popular architectures for image generation, which has achieved significant progress in generating high-resolution, diverse image samples. The normal GANs are supposed to minimize the Kullback–Leibler
Likun Cai   +4 more
doaj   +1 more source

SpaMode: A Broadly Applicable Framework for Deciphering Spatial Multi‐Omics Using Multimodal Mixture of Disentangled Experts

open access: yesAdvanced Science, EarlyView.
SpaMode introduces a versatile framework for spatial multi‐omics integration across vertical, horizontal, and mosaic scenarios. By disentangling modality‐invariant and variant features through a mixture‐of‐experts mechanism, it adaptively reconfigures spatially heterogeneous signals.
Xubin Zheng   +6 more
wiley   +1 more source

Distributed Vector Quantization Based on Kullback-Leibler Divergence

open access: yesEntropy, 2015
The goal of vector quantization is to use a few reproduction vectors to represent original vectors/data while maintaining the necessary fidelity of the data.
Pengcheng Shen   +2 more
doaj   +1 more source

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

open access: yesAdvanced 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   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy