Results 51 to 60 of about 235,048 (260)
Semi-Supervised Deep Representation Learning
, 2019 Deep neural networks need a lot of data to show their full potential in modeling and solving problems. However, in many real-world applications labeling data is expensive or not feasible while abundant unlabeled data is available.
Vahid Noroozi (8973485)
core +1 more source
Augmentation Learning for Semi-Supervised Classification
, 2022 Recently, a number of new Semi-Supervised Learning methods have emerged. As the accuracy for ImageNet and similar datasets increased over time, the performance on tasks beyond the classification of natural images is yet to be explored. Most Semi-Supervised Learning methods rely on a carefully manually designed data augmentation pipeline that is not ...
Tim Frommknecht +4 more
openaire +2 more sources
Advanced Healthcare Materials, EarlyView.We describe a microfluidic tumor‐stroma co‐culture model, engineered to resist collagen‐hydrogel contraction driven by fibroblast activity. Surface silanization with APTES covalently anchors the matrix to the chip, while Genipin crosslinking progressively increases stiffness and elasticity without harming cells. This supports >10 days of co‐culture and
Doriane Le Manach +4 more
wiley +1 more source
Weakly Supervised Learning of Objects, Attributes and their Associations
, 2014 . When humans describe images they tend to use combinations of nouns and adjectives, corresponding to objects and their associated attributes respectively.
Zhiyuan Shi +11 more
core +1 more source
A discriminative model for semi-supervised learning [PDF]
Journal of the ACM, 2010 Supervised learning—that is, learning from labeled examples—is an area of Machine Learning that has reached substantial maturity. It has generated general-purpose and practically successful algorithms and the foundations are quite well understood and captured by theoretical frameworks such as the PAC-learning model and the Statistical ...
Maria-Florina Balcan, Avrim Blum
openaire +1 more source
Microengineered Gradient Hydrogels for Mechanobiology
Advanced Healthcare Materials, EarlyView.Gradient hydrogels are used to mimic the mechanical heterogeneity in native tissues, offering powerful in vitro platforms to study cell‐material interactions in diverse pathophysiological contexts. Here, we present a comprehensive review of the design and experimental considerations for stiffness gradient hydrogels, discussing exemplary achievements ...
Shin Wei Chong +4 more
wiley +1 more source
Semi-Supervised Learning on Riemannian Manifolds [PDF]
Machine Learning, 2004 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Mikhail Belkin, Partha Niyogi
openaire +2 more sources
Advanced Materials, EarlyView.Molecular doping of conjugated polymers is fundamentally constrained by thermodynamic phase behavior. This Perspective reframes doping efficiency and stability in terms of miscibility limits, binodals, and solvus boundaries, highlighting the role of effective interaction parameters and charge transfer.
Somayeh Kashani +10 more
wiley +1 more source
Semi-supervised Continual Learning with Meta Self-training
, 2022 Semi-supervised Continual Learning with Meta Self ...
Yunfeng Li (37710) +5 more
core +1 more source
Nanomaterial Integration at Liquid–Liquid Interfaces for Green Catalysis
Advanced Materials, EarlyView.Functional nanomaterials assembled at liquid–liquid interfaces create dual‐role platforms serving as emulsion stabilizers and catalytic sites, offering enhanced reaction kinetics with improved catalyst recovery and recyclability. This review examines design strategies, structure‐performance relationships, and industrial implementation prospects of ...
Bokgi Seo +6 more
wiley +1 more source