Results 101 to 110 of about 44,296 (265)

Semi-Supervised Learning with Ladder Networks

CoRR, 2015
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training.
Antti Rasmus, Mathias Berglund, Mikko Honkala, Harri Valpola, Tapani Raiko   +4 more
openaire   +3 more sources

Time‐Multiplexed Organic Electrochemical Transistor for Saliva‐Based Rapid Detection of Viral Proteins

Advanced Science, EarlyView.
A time‐multiplexed nanobody‐functionalized organic electrochemical transistor enables rapid and sensitive detection of three respiratory viral proteins from saliva. Sequentially addressed multi‐gate electrodes on a shared channel achieve around 1 fm detection within 15 min without sample preprocessing. Clinical validation demonstrates high specificity,
Tianrui Chang, Yuxiang Ren, Shofarul Wustoni, Atheer Alqatari, Adel Hama, Yazhou Wang, Long Chen, Jessica Parrado Agudelo, Luca Salvigni, Keying Guo, Ashraf Dada, Stefan T. Arold, Raik Grünberg, Sahika Inal   +13 more
wiley   +1 more source

An Integrated NLP‐ML Framework for Property Prediction and Design of Steels

Advanced Science, EarlyView.
This study presents a data‐driven framework that uses language‐processing techniques to interpret steel processing descriptions and machine‐learning models to predict mechanical properties. By organising complex process histories into meaningful groups and enabling rapid property forecasts, the work supports faster, more informed steel design through ...
Kiran Devraju, Adithya Umanath Rai, Jose Thomson, Marzie Ghorbani, Shujing Zhao, Nick Birbilis   +5 more
wiley   +1 more source

Stress History Establishes a Transient Tolerant State That Shapes Antibiotic Survival Upon Resuscitation

Advanced Science, EarlyView.
High‐throughput single‐cell analysis of resuscitating bacteria reveals a starvation‐history‐dependent transiently tolerant subpopulation that survives β$\beta$‐lactam exposure by temporarily reducing growth. Distinct from classical persisters, these actively growing yet dynamically modulated cells dominate survival across clinically relevant antibiotic
Kieran Abbott, Georgeos Hardo, Ruizhe Li, Jack Bradley, Ashraf Zarkan, Somenath Bakshi   +5 more
wiley   +1 more source

Semi-Supervised Apprenticeship Learning.

, 2012
In apprenticeship learning we aim to learn a good policy by observing the behavior of an expert or a set of experts. In particular, we consider the case where the expert acts so as to maximize an unknown reward function defined as a linear combination of a set of state features.
Valko, Michal, Ghavamzadeh, Mohammad, Lazaric, Alessandro   +2 more
openaire   +2 more sources

A topological approach for semi-supervised learning

Journal of Computational Science
Nowadays, Machine Learning and Deep Learning methods have become the state-of-the-art approach to solve data classification tasks. In order to use those methods, it is necessary to acquire and label a considerable amount of data; however, this is not straightforward in some fields, since data annotation is time consuming and might require expert ...
Adrián Inés, César Domínguez 0001, Jónathan Heras, Gadea Mata, Julio Rubio 0001   +4 more
openaire   +4 more sources

Deciphering Short‐Range Order in 2D Transition Metal Dichalcogenides: From Origin to Multi‐Scale Property Modulation

Advanced Science, EarlyView.
Short‐range order in 2D transition metal dichalcogenides is revealed as a new design paradigm. Driven by chemical affinity and atomic size, it governs properties across scales. Weak ordering tunes site‐resolved magnetism and d‐band centers, while strong ordering eliminates gap states to open band gaps.
Hanyu Liu, Linggang Zhu, Jian Zhou, Zhimei Sun   +3 more
wiley   +1 more source

Reinforcement Learning Guided Semi-Supervised Learning

Advances in Neural Information Processing Systems 37
In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especially when labeled data is scarce. However, most current SSL methods rely on heuristics or predefined rules for generating pseudo-labels and leveraging unlabeled data.
Marzi Heidari, Hanping Zhang, Yuhong Guo
openaire   +3 more sources

Transferable Deep Reinforcement Learning With Edge‐Contour‐Depth Fusion for Autonomous Wireless Capsule Endoscopy Navigation

Advanced Science, EarlyView.
This study presents an anatomical landmark‐guided DRL framework for autonomous wireless capsule endoscopy navigation. Using a lightweight edge‐contour‐depth fusion module, it achieves over 97% coverage across diverse gastric anatomies. To ensure reliability, a two‐stage sim‐to‐real pipeline with an adaptive dynamic programming controller mitigates ...
Haoxuan Wu, Haitao Gao, Qingyang Liu, Sishen Yuan, Haiyang Fang, Mingwu Su, Baijia Liang, Yongzun Yang, Long Bai, Wenzhen Dong, Dihong Xie, Shijian Su, Jiewen Lai, Shing Shin Cheng, Zhen Li, Xiuli Zuo, Hongliang Ren   +16 more
wiley   +1 more source

Physics‐Constrained Constitutive Learning of Rate‐Limiting Timescales for Efficient Hydrogen‐Based Direct Reduction for Green Steel Making

Advanced Science, EarlyView.
A conversion‐resolved constitutive framework is developed for the hydrogen‐based direct reduction of iron oxide pellets. Effective reaction and transport timescales are inferred directly from measured trajectories and mapped against operating conditions, pellet architecture, and composition. The analysis reveals how late‐stage transport control emerges
Anurag Bajpai, Barak Ratzker, Pasquale Cavaliere, Dierk Raabe   +3 more
wiley   +1 more source