Results 131 to 140 of about 921,222 (281)

Lightweight Bayesian SAR Image Object Detection and Recognition Method Based on Heavy-Tail Prior and Variational Inference

open access: yesRemote Sensing
Traditional Bayesian SAR detection methods suffer poor adaptability to speckle noise, fail to handle severe class imbalance within large-scale multi-target datasets, and incur prohibitive training overheads.
Jiaqi Fang, Hemin Sun, Hongquan Li
doaj   +1 more source

An AI‐Driven Framework for Directed Self‐Assembly Toward Design‐Technology Co‐Optimization

open access: yesAdvanced Science, EarlyView.
An artificial intelligence (AI)‐driven closed‐loop framework integrates experiment, three‐dimensional physics‐based simulation, and template design for directed self‐assembly (DSA). Guided by experimental data, AI‐assisted calibration accelerates model optimization, supports morphology prediction, and identifies template windows.
Caiwei Shang   +9 more
wiley   +1 more source

Gapless Complete Genome and Multi‐Omics Illuminate Immune Adaptation and Host‐Virus Interactions in a Coronavirus Reservoir

open access: yesAdvanced Science, EarlyView.
We present a complete T2T genome assembly for a key bat reservoir. Integrating population genomics, comparative genomics, transcriptomics, single‐cell omics, and functional assays, we resolve previously inaccessible genomic regions and identify evolutionary signatures associated with immune adaptation.
Yuting Wang   +15 more
wiley   +1 more source

Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows

open access: yes, 2020
Variational Bayesian phylogenetic inference (VBPI) provides a promising general variational framework for efficient estimation of phylogenetic posteriors. However, the current diagonal Lognormal branch length approximation would significantly restrict the quality of the approximating distributions. In this paper, we propose a new type of VBPI, VBPI-NF,
openaire   +3 more sources

SpaCut: Transcript‐Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics

open access: yesAdvanced Science, EarlyView.
Subcellular spatial transcriptomics enables high‐resolution mapping of gene expression within tissues, but accurate cell segmentation is essential for assigning transcripts to individual cells. We present SpaCut, a deep learning framework that integrates transcriptomic features with nucleus‐guided morphological information to precisely delineate cell ...
Yongheng Li, Fangfang Zhu, Wenwen Min
wiley   +1 more source

A Novel Bearing Fault Diagnosis Method Based on Improved Convolutional Neural Network and Multi-Sensor Fusion

open access: yesMachines
Bearings are key components of modern mechanical equipment. To address the issue that the limited information contained in the single-source signal of the bearing leads to the limited accuracy of the single-source fault diagnosis method, a multi-sensor ...
Zhongyao Wang   +4 more
doaj   +1 more source

Device Stochasticity Directly Implements Bayesian Sampling in Spiking Neurons

open access: yesAdvanced Science, EarlyView.
Brain‐inspired stochastic spiking turns device noise into Bayesian uncertainty for robust, low‐power neuromorphic computing. ABSTRACT Device stochasticity is considered a non‐ideality in neuromorphic hardware, although stochastic neural activity supports probabilistic computation in biological systems.
Huannan Zheng, Jingli Liu, Kezhou Yang
wiley   +1 more source

Efficient Approximate Inference with Walsh-Hadamard Variational Inference

open access: yes, 2019
International audienceVariational inference offers scalable and flexible tools to tackle intractable Bayesian inference of modern statistical models like Bayesian neural networks and Gaussian processes. For largely over-parameterized models, however, the
Filippone, Maurizio   +2 more
core   +2 more sources

Variable Bayesian-Based Maximum Correntropy Criterion Cubature Kalman Filter with Application to Target Tracking

open access: yesEntropy
Target tracking in typical radar applications faces critical challenges in complex environments, including nonlinear dynamics, non-Gaussian noise, and sensor outliers.
Yu Ma   +3 more
doaj   +1 more source

A Variational Approach to Bayesian Phylogenetic Inference [PDF]

open access: yes
Bayesian phylogenetic inference is currently done via Markov chain Monte Carlo (MCMC) with simple proposal mechanisms. This hinders exploration efficiency and often requires long runs to deliver accurate posterior estimates.
Matsen IV, Frederick A., Zhang, Cheng
core  

Home - About - Disclaimer - Privacy