Results 121 to 130 of about 3,949,706 (285)

Adaptive Unsupervised Feature Selection with Structure Regularization

open access: yes, 2018
© 2012 IEEE. Feature selection is one of the most important dimension reduction techniques for its efficiency and interpretation. Since practical data in large scale are usually collected without labels, and labeling these data are dramatically expensive
Chang, X   +5 more
core   +1 more source

SemanticST: A Scalable Multi‐Contextual Graph Learning Framework for Uncovering Spatial Niches and Robust Multi‐Sample Integration in Spatial Transcriptomics

open access: yesAdvanced Science, EarlyView.
Technical limitations often let dominant signals overshadow rare cell types and fine‐grained heterogeneity in spatial transcriptomics. SemanticST, a graph neural network using multi‐semantic graph fusion and a novel min‐cut loss, recovers these subtle patterns.
Roxana Zahedi   +7 more
wiley   +1 more source

Neuromorphic Devices and Computing for Sensing, Memory, and Control

open access: yesAdvanced Science, EarlyView.
This review introduces neuromorphic devices made from diverse materials. These devices mimic neuronal functions and architectures and, when integrated with artificial or biological computing, can form closed loops with neurons for pressure, optical, acoustic, and biochemical sensing and modulation.
Zhengguang Zhu   +2 more
wiley   +1 more source

Consensus Guided Multi-View Unsupervised Feature Selection with Hybrid Regularization

open access: yesApplied Sciences
Multi-source heterogeneous data has been widely adopted in developing artificial intelligence systems in recent years. In real-world scenarios, raw multi-source data are generally unlabeled and inherently contain multi-view noise and feature redundancy ...
Yifan Shi   +7 more
doaj   +1 more source

ℓ2,1-Norm regularized discriminative feature selection for unsupervised learning

open access: yes, 2011
Compared with supervised learning for feature selection, it is much more difficult to select the discriminative features in unsupervised learning due to the lack of label information.
Ma, Zhigang   +9 more
core   +1 more source

Uncoupling Type I Interferon Benefits From Inflammatory Toxicity: Transformer‐Prioritized Precision Agonists for Potent and Safer Cancer Immunotherapy

open access: yesAdvanced Science, EarlyView.
A Transformer‐based AI framework, DLINP, screens millions of compounds to identify Co68, a cobalt‐pincer organometallic complex that biases TLR4‐MD2 signaling toward antitumor interferon activation while suppressing inflammatory toxicity through an early TLR4‐SYK‐STAT1 axis.
Xuefei Guo   +10 more
wiley   +1 more source

An incremental approach to MSE-based feature selection [PDF]

open access: yes, 2007
Feature selection plays an important role in classification systems. Using classifier error rate as the evaluation function, feature selection is integrated with incremental training.
Guan, SU, Bao, C, Qi, Y
core   +1 more source

Tissue‐Agnostic Cellular Morphometric Biomarkers for Risk‐Adapted Management Across Gastrointestinal Precancerous Lesions and Cancers

open access: yesAdvanced Science, EarlyView.
An interpretable, unsupervised artificial intelligence framework identifies a 13‐cellular morphometric biomarker (CMB) signature from routine H&E whole‐slide images. Validated across 2,602 patients, the fixed signature generalizes across colorectal, gastric, and esophageal tissues without retraining, stratifies prognosis and precancerous lesion risk ...
Pin Wang   +14 more
wiley   +1 more source

Home - About - Disclaimer - Privacy