Results 121 to 130 of about 51,507 (261)

A predictive model for post-thoracoscopic surgery pulmonary complications based on the PBNN algorithm

Scientific Reports
We constructed an early prediction model for postoperative pulmonary complications after thoracoscopic surgery using machine learning and deep learning algorithms.
Cheng-Mao Zhou, Qiong Xue, HuiJuan Li, Jian-Jun Yang, Yu Zhu   +4 more
doaj   +1 more source

A Bayesian neural network predicts the dissolution of compact planetary systems. [PDF]

Proc Natl Acad Sci U S A, 2021
Cranmer M, Tamayo D, Rein H, Battaglia P, Hadden S, Armitage PJ, Ho S, Spergel DN.   +7 more
europepmc   +1 more source

Terahertz Channel Modeling, Estimation and Localization in RIS‐Assisted Systems

Advanced Electronic Materials, EarlyView.
Reconfigurable intelligent surfaces have become a recent intensive research focus. Based on practical applications, channel strategies for RIS‐assisted terahertz wireless communication systems are categorized into three different types: channel modeling, channel estimation, and channel localization.
Hongjing Wang, Weipeng Wang, Xuan Cong, Shiyu Wang, Gao Li, Sen Gong, Lin Huang, Hongxin Zeng, Yaxin Zhang, Ziqiang Yang   +9 more
wiley   +1 more source

Modeling rapid language learning by distilling Bayesian priors into artificial neural networks

Nature Communications
Humans can learn languages from remarkably little experience. Developing computational models that explain this ability has been a major challenge in cognitive science.
R. Thomas McCoy, Thomas L. Griffiths
doaj   +1 more source

Hyperparameter Optimization of Bayesian Neural Network Using Bayesian Optimization and Intelligent Feature Engineering for Load Forecasting. [PDF]

Sensors (Basel), 2022
Zulfiqar M, Gamage KAA, Kamran M, Rasheed MB.   +3 more
europepmc   +1 more source

Emerging Memory and Device Technologies for Hardware‐Accelerated Model Training and Inference

Advanced Electronic Materials, EarlyView.
This review investigates the suitability of various emerging memory technologies as compute‐in‐memory hardware for artificial intelligence (AI) applications. Distinct requirements for training‐ and inference‐centric computing are discussed, spanning device physics, materials, and system integration.
Yoonho Cho, Dae‐won Kim, Yujin Kim, Jung‐Heum Na, Yuwon Jeong, Dong‐Yeop Lee, Shinhyun Choi   +6 more
wiley   +1 more source

Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction. [PDF]

Bioinformatics, 2021
Kim Q, Ko JH, Kim S, Park N, Jhe W.
europepmc   +1 more source

Artificial Intelligence for Fluorite Ferroelectric Materials: From Discovery to Optimization

Advanced Electronic Materials, EarlyView.
Artificial intelligence accelerates the discovery and optimization of HfO2‐based fluorite ferroelectrics by linking synthesis, structure, properties, and device performance. Machine learning, deep‐learning analysis, and AI‐driven atomistic modeling enable predictive design, dopant screening, and closed‐loop optimization toward next‐generation ...
Faizan Ali, David Lehninger, Florencio Sánchez, Ignasi Fina   +3 more
wiley   +1 more source

Uncertainty quantified discovery of chemical reaction systems via Bayesian scientific machine learning

Frontiers in Systems Biology
The recently proposed Chemical Reaction Neural Network (CRNN) discovers chemical reaction pathways from time resolved species concentration data in a deterministic manner. Since the weights and biases of a CRNN are physically interpretable, the CRNN acts
Emily Nieves, Emily Nieves, Raj Dandekar, Chris Rackauckas   +3 more
doaj   +1 more source

Assessing Mesoscale Heterogeneities in Hard Carbon Electrodes Through Deep Learning‐Assisted FIB‐SEM Characterization, Manufacturing and Electrochemical Modeling

Advanced Energy Materials, EarlyView.
A combination of discrete and finite element method models for the current collector deformation and electrochemical performance analysis, respectively. The models are calibrated and validated with electrochemical and imaging data of hard carbon electrodes. These electrodes were manufactured with different parameters (slurry solid contents of 35 and 40
Soorya Saravanan, Imelda Cardenas‐Sierra, Pei Sun, Hari Raj, Daniele Duranti, Mahnoor Nafees, Edoardo Rossi, Marco Sebastiani, Paul Vigneaux, Martin Petit, Maxime Moreaud, Francisco Fernandez, Alejandro A. Franco   +12 more
wiley   +1 more source