Results 91 to 100 of about 5,885,991 (322)

Weakly Supervised Dictionary Learning [PDF]

IEEE Transactions on Signal Processing, 2018
We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising and restoration as well as high-level classification tasks, which can be applied to audio and image analysis ...
Zeyu You, Raviv Raich, Xiaoli Z. Fern, Jinsub Kim   +3 more
openaire   +2 more sources

Decrypting cancer's spatial code: from single cells to tissue niches

Molecular Oncology, EarlyView.
Spatial transcriptomics maps gene activity across tissues, offering powerful insights into how cancer cells are organised, switch states and interact with their surroundings. This review outlines emerging computational, artificial intelligence (AI) and geospatial approaches to define cell states, uncover tumour niches and integrate spatial data with ...
Cenk Celik, Shi Pan, Eloise Withnell, Hou Wang Lam, Maria Secrier   +4 more
wiley   +1 more source

Galaxy-ML: An accessible, reproducible, and scalable machine learning toolkit for biomedicine.

PLoS Computational Biology, 2021
Supervised machine learning is an essential but difficult to use approach in biomedical data analysis. The Galaxy-ML toolkit (https://galaxyproject.org/community/machine-learning/) makes supervised machine learning more accessible to biomedical ...
Qiang Gu, Anup Kumar, Simon Bray, Allison Creason, Alireza Khanteymoori, Vahid Jalili, Björn Grüning, Jeremy Goecks   +7 more
doaj   +1 more source

Tumor‐agnostic detection of circulating tumor DNA in patients with advanced pancreatic cancer using targeted DNA methylation sequencing and cell‐free DNA fragmentomics

Molecular Oncology, EarlyView.
We evaluated circulating tumor DNA (ctDNA) detection in advanced pancreatic cancer using DNA methylation, cell‐free DNA fragment lengths, and 5′ end motifs. Machine learning models were trained to estimate ctDNA levels from each feature and their combination.
Morten Lapin, Kjersti Tjensvoll, Karin Hestnes Edland, Satu Oltedal, Herish Garresori, Bjørnar Gilje, Saga Ekedal, Trygve Eftestøl, Jan Terje Kvaløy, Filip Janku, Oddmund Nordgård   +10 more
wiley   +1 more source

Supervised Competitive Learning

Journal of Intelligent Material Systems and Structures, 1994
Supervised Competitive Learning (SCL) assembles a set of learning modules into a supervised learning system to address the stability-plasticity dilemma. Each learning module acts as a similarity detector for a prototype, and includes prototype resetting (akin to that of ART) to re spond to new prototypes.
Fuller, Thomas H., Jr., Kimura, Takayuki D.   +1 more
openaire   +3 more sources

Starting From Scratch: A White Woman's Journey to Build a Teaching Center Rooted in Adult Learning and Feminist Theories at an HBCU

New Directions for Adult and Continuing Education, EarlyView.
ABSTRACT This autobiographical article recounts a White woman's efforts to establish a center for teaching and learning (CTL) in a large HBCU in the southern part of the United States. She describes the ways in which tenets of critical feminism, feminist pedagogies, and adult learning and development informed her approach to faculty development.
Audrey Dentith
wiley   +1 more source

BCS1L‐Associated Disease: 5′‐UTR Variant Shifts the Phenotype Towards Axonal Neuropathy

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objectives To investigate the consequences of a pathogenic missense variant (c.838C>T; p.L280F) and a 5′‐UTR regulatory variant (c.‐122G>T) in BCS1L on disease pathogenesis and to understand how regulatory variants influence disease severity and clinical presentation.
Rotem Orbach, Nunziata Maio, Russell J. Butterfield, A. Reghan Foley, Sarah Silverstein, Yan Li, Katherine Chao, Tanya J. Lehky, Abigail Potticary, Tracey A. Rouault, Sandra Donkervoort, Carsten G. Bönnemann   +11 more
wiley   +1 more source

A Semi-Supervised-Learning-Aided Explainable Belief Rule-Based Approach to Predict the Energy Consumption of Buildings

Algorithms
Predicting the energy consumption of buildings plays a critical role in supporting utility providers, users, and facility managers in minimizing energy waste and optimizing operational efficiency. However, this prediction becomes difficult because of the
Sami Kabir, Mohammad Shahadat Hossain, Karl Andersson   +2 more
doaj   +1 more source

Quantitative Shape Irregularity and Density Heterogeneity Predict Hematoma Expansion in Patients With Intracerebral Hemorrhage

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Purpose This study aimed to explore the association between quantitative shape irregularity and density heterogeneity of hematomas and hematoma expansion (HE) for intracerebral hemorrhage (ICH) patients. Methods This cohort study included patients arriving within 24 h of symptom onset between August 2021 and July 2022 as the derivation cohort ...
Zeqiang Ji, Yunyi Hao, Bin Gao, Xiaojing Zhang, Yani Zhang, Jiaokun Jia, Xue Xia, Yuhao Guo, Sijia Li, Jianwei Wu, Kaijiang Kang, Xingquan Zhao   +11 more
wiley   +1 more source

Exploring if Longitudinal Changes on PET Imaging Can Serve as a Biomarker for Stiff Person Syndrome Spectrum Disorders

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective To identify metabolic patterns in the brain and musculoskeletal system of stiff person syndrome spectrum disorders (SPSD) patients over time using PET imaging and evaluate the impact of immune therapy on metabolic activity as a surrogate for treatment response.
Munther M. Queisi, Samantha N. Roman, Mohammad S. Sadaghiani, Lilja B. Solnes, Scott D. Newsome   +4 more
wiley   +1 more source