Results 61 to 70 of about 215,845 (322)

A comparative analysis of deep learning architectures with data augmentation and multichannel input for locoregional breast cancer radiotherapy

Journal of Applied Clinical Medical Physics, EarlyView.
Abstract Purpose Studies on deep learning dose prediction increasingly focus on 3D models with multiple input channels and data augmentation, which increases the training time and thus also the environmental burden and hampers the ease of re‐training. Here we compare 2D and 3D U‐Net models with clinical accepted plans to evaluate the appropriateness of
Rosalie Klarenberg, Nienke L. M. Bakx, Coen W. Hurkmans   +2 more
wiley   +1 more source

Cerebello‐Prefrontal Connectivity Underlying Cognitive Dysfunction in Spinocerebellar Ataxia Type 2

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Spinocerebellar ataxia type 2 (SCA2) is a hereditary cerebellar degenerative disorder, with motor and cognitive symptoms. The constellation of cognitive symptoms due to cerebellar degeneration is named cerebellar cognitive affective syndrome (CCAS), which has increasingly been recognized to profoundly impact patients' quality of life;
Ami Kumar, Ruo‐Yah Lai, Zena Fadel, Yicheng Lin, Pia Parekh, Rachel Griep, Ming‐Kai Pan, Sheng‐Han Kuo   +7 more
wiley   +1 more source

Capsule GAN Using Capsule Network for Generator Architecture [PDF]

arXiv, 2020
This paper presents Capsule GAN, a Generative adversarial network using Capsule Network not only in the discriminator but also in the generator. Recently, Generative adversarial networks (GANs) has been intensively studied. However, generating images by GANs is difficult. Therefore, GANs sometimes generate poor quality images.
arxiv  

MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets [PDF]

IEEE International Parallel and Distributed Processing Symposium (IPDPS) 2019, 2018
A recent technical breakthrough in the domain of machine learning is the discovery and the multiple applications of Generative Adversarial Networks (GANs). Those generative models are computationally demanding, as a GAN is composed of two deep neural networks, and because it trains on large datasets. A GAN is generally trained on a single server.
arxiv   +1 more source

Electronic and magnetic properties GaN/MnN/GaN and MnN/GaN/MnN interlayers [PDF]

Journal of Physics: Conference Series, 2016
In this work we execute computational calculations to investigate the structural, electronic and magnetic properties of the GaN/MnN/GaN and MnN/GaN/MnN interlayers. The calculations were carried out by a method based on pseudopotentials, as implemented in the Quantum ESPRESSO code.
G. Casiano Jiménez, M J Espitia, C. Ortega López   +2 more
openaire   +1 more source

Bridging Nature and Technology: A Perspective on Role of Machine Learning in Bioinspired Ceramics

Advanced Engineering Materials, EarlyView.
Machine learning (ML) is revolutionizing the development of bioinspired ceramics. This article investigates how ML can be used to design new ceramic materials with exceptional performance, inspired by the structures found in nature. The research highlights how ML can predict material properties, optimize designs, and create advanced models to unlock a ...
Hamidreza Yazdani Sarvestani, Aditi Singh, Behnam Ashrafi   +2 more
wiley   +1 more source

Исследования остаточных упругих напряжений в многопериодных сверхрешетках GaN/AlN, выращенных на подложке SiC/Si

Конденсированные среды и межфазные границы
Впервые методом хлорид-гидридной эпитаксии на гибридной подложке SiC/Si, синтезированной методом согласованного замещения атомов, сформирована многослойная гетероструктура, состоящая из периодически расположенных слоев GaN и AlN.
Павел Владимирович Середин, Шукрилло Шамсидинович Шарофидинов, Дмитрий Леонидович Голощапов, Никита Сергеевич Буйлов, Константин Александрович Еремеев, Шаира Абдувалиевна Юсупова, Сергей Арсеньевич Кукушкин   +6 more
doaj   +1 more source

The Role of GaN in the Heterostructure WS2/GaN for SERS Applications

Materials, 2023
In the application of WS2 as a surface–enhanced Raman scattering (SERS) substrate, enhancing the charge transfer (CT) opportunity between WS2 and analyte is an important issue for SERS efficiency. In this study, we deposited few-layer WS2 (2–3 layers) on GaN and sapphire substrates with different bandgap characteristics to form heterojunctions using a ...
Tsung-Shine Ko, En-Ting Lin, Yen-Teng Ho, Chen-An Deng   +3 more
openaire   +2 more sources

Trans‐Conductive Melt Pool Scaling and its Implications for Parameter Transfer in Laser Powder Bed Fusion for Metals with High Thermal Diffusivity

Advanced Engineering Materials, EarlyView.
Developing process parameters for the laser‐based Powder Bed Fusion of metals can be a tedious task. Based on melt pool depth, the process parameters are transferable to different laser scan speeds. For this, understanding the melt pool scaling behavior is essential, particularly for materials with high thermal diffusivity, as a change in scaling ...
Markus Döring, Matthias Gehring, Michael Schmidt   +2 more
wiley   +1 more source

Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder [PDF]

arXiv, 2020
We propose Unbalanced GANs, which pre-trains the generator of the generative adversarial network (GAN) using variational autoencoder (VAE). We guarantee the stable training of the generator by preventing the faster convergence of the discriminator at early epochs.
arxiv