Results 11 to 20 of about 820,067 (303)

Using deep learning algorithms for texture segmentation of ultra-high resolution satellite images [PDF]

E3S Web of Conferences, 2021
This paper presents the results of textural segmentation of satellite images with spatial resolution
Rusin Dmitry, Alehina Anna, Safonova Anastasia, Dmitriev Egor   +3 more
doaj   +1 more source

Implicit Deep Learning [PDF]

SIAM Journal on Mathematics of Data Science, 2021
Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks. Such rules are based on the solution of a fixed-point equation involving a single vector of hidden features, which is thus only implicitly defined.
Laurent El Ghaoui, Fangda Gu, Bertrand Travacca, Armin Askari, Alicia Tsai   +4 more
openaire   +3 more sources

Deep, deep learning with BART

Magnetic Resonance in Medicine, 2022
PurposeTo develop a deep‐learning‐based image reconstruction framework for reproducible research in MRI.MethodsThe BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and compressed sensing.
Blumenthal, Moritz, Luo, Guanxiong, Schilling, Martin, Holme, H. Christian M., Uecker, Martin, Luo, Guanxiong; 1 Institute for Diagnostic and Interventional Radiology University Medical Center Göttingen Göttingen Germany, Schilling, Martin; 1 Institute for Diagnostic and Interventional Radiology University Medical Center Göttingen Göttingen Germany, Holme, H. Christian M.; 2 Institute of Biomedical Imaging Graz University of Technology Graz Austria   +7 more
openaire   +5 more sources

ParaMed: a parallel corpus for English–Chinese translation in the biomedical domain

BMC Medical Informatics and Decision Making, 2021
Background Biomedical language translation requires multi-lingual fluency as well as relevant domain knowledge. Such requirements make it challenging to train qualified translators and costly to generate high-quality translations.
Boxiang Liu, Liang Huang
doaj   +1 more source

Deep Cascade Learning [PDF]

IEEE Transactions on Neural Networks and Learning Systems, 2018
In this paper, we propose a novel approach for efficient training of deep neural networks in a bottom-up fashion using a layered structure. Our algorithm, which we refer to as deep cascade learning, is motivated by the cascade correlation approach of Fahlman and Lebiere, who introduced it in the context of perceptrons.
Enrique S. Marquez, Jonathon S. Hare, Mahesan Niranjan   +2 more
openaire   +4 more sources

Unsupervised Anomaly Detection Using Style Distillation

IEEE Access, 2020
Autoencoders (AEs) have been widely used for unsupervised anomaly detection. They learn from normal samples such that they produce high reconstruction errors for anomalous samples.
Hwehee Chung, Jongho Park, Jongsoo Keum, Hongdo Ki, Seokho Kang   +4 more
doaj   +1 more source

Effective prediction finite element model of pull-out capacity for cast-in-place anchor in high strain rate effects

Scientific Reports, 2023
Cast-in-place anchors are being increasingly used in many applications including building construction, bridge, and power plants. The anchorage to concrete systems are subjected to tensile, shear and combined loads from a variety of loading circumstances
Quoc To Bao, Kihak Lee, Hyoseo An, Do Hyung Lee, Jiuk Shin   +4 more
doaj   +1 more source

Multiagent Reinforcement Learning for Strategic Decision Making and Control in Robotic Soccer Through Self-Play

IEEE Access, 2022
Reinforcement Learning (RL) has shown promising performance in environments for both robotic control and strategic decision making. However, they are usually treated as separate problems with different objectives.
Bruno Brandao, Telma Woerle De Lima, Anderson Soares, Luckeciano Melo, Marcos R. O. A. Maximo   +4 more
doaj   +1 more source

An Improved Blind Kriging Surrogate Model for Design Optimization Problems

Mathematics, 2022
Surrogate modeling techniques are widely employed in solving constrained expensive black-box optimization problems. Therein, Kriging is among the most popular surrogates in which the trend function is considered as a constant mean.
Hau T. Mai, Jaewook Lee, Joowon Kang, H. Nguyen-Xuan, Jaehong Lee   +4 more
doaj   +1 more source

Short-sighted deep learning [PDF]

Physical Review E, 2020
A theory explaining how deep learning works is yet to be developed. Previous work suggests that deep learning performs a coarse graining, similar in spirit to the renormalization group (RG). This idea has been explored in the setting of a local (nearest neighbor interactions) Ising spin lattice.
Ellen de Mello Koch, Anita de Mello Koch, Nicholas Kastanos, Ling Cheng   +3 more
openaire   +3 more sources