Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study. by Andrew G Taylor, Clinton Mielke, John Mongan

“…This dataset was used to train and evaluate multiple network architectures. Images showing large- or moderate-sized pneumothorax were considered positive, and those with trace or no pneumothorax were considered negative. …”
Get full text

Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists. by Pranav Rajpurkar, Jeremy Irvin, Robyn L Ball, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan, Daisy Ding, Aarti Bagul, Curtis P Langlotz, Bhavik N Patel, Kristen W Yeom, Katie Shpanskaya, Francis G Blankenberg, Jayne Seekins, Timothy J Amrhein, David A Mong, Safwan S Halabi, Evan J Zucker, Andrew Y Ng, Matthew P Lungren

“…Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. …”
Get full text

Optimising convolutional neural networks for large-scale neuroimaging studies by Dinsdale, NK

“…The framework is demonstrated for regression, classification, and segmentation tasks with two different network architectures. It is shown that not only can the framework harmonise multi-site datasets, but it can also adapt to many data scenarios, including biased datasets and limited training labels. …”

Advanced Fractional Mathematics, Fractional Calculus, Algorithms and Artificial Intelligence with Applications in Complex Chaotic Systems by Dumitru Baleanu, Yeliz Karaca

“…Therefore, chaos-based algorithms are employed for the optimization of neural network architectures and training processes. Fractional mathematics, with the application of fractional calculus techniques geared towards the problems’ solutions, describes the existence characteristics of complex natural, applied sciences, scientific, engineering related and medical systems more accurately to reflect the actual state properties co-evolving entities and patterns of the systems concerning nonlinear dynamic systems and modeling complexity evolution with fractional chaotic and complex systems. …”
Get full text

Incorporating external knowledge into machine learning algorithms for NLP applications by Li, Pengfei

“…The commonly adopted deep neural network architectures include Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Transformer. …”
Get full text

Towards diverse generation and reliable classification using neural networks by Kulharia, V

“…Extensive experiments on a variety of computer vision and NLP datasets, and with a wide variety of network architectures, justify that this approach achieves state-of-the-art calibration without compromising accuracy in almost all cases.…”

Research of U-Net-Based CNN Architectures for Metal Surface Defect Detection by Ihor Konovalenko, Pavlo Maruschak, Janette Brezinová, Olegas Prentkovskis, Jakub Brezina

“…Over the past 10 years, researchers have proposed a number of neural network architectures that have shown high efficiency in various areas, including image classification, segmentation and recognition. …”
Get full text

Survivable Path Sets: A New Approach to Survivability in Multilayer Networks by Hyang-Won Lee, Marzieh, Parandehgheibi, Marzieh, Modiano, Eytan H

“…One of the most important advances in modern communication networks is embedding multilayer network architectures such as IP-over-WDM.1 In these layered networks, a logical topology is embedded onto a physical topology such that each logical link is routed using a path in the physical topology. …”
Get full text
Get full text
Get full text

Towards Reliable AI via Efficient Verification of Binarized Neural Networks by Jia, Kai

“…We also show that it is possible to craft neural network architectures and weights that cause an unsound incomplete verifier to produce incorrect verification results. …”
Get full text
Get full text

Uncertainty quantification for complex systems : application to the study of cities by Steentoft, Aike Alexander

“…I tested various implementations of network architectures and inference procedures on synthetic data sets and a real data set related to human interactivity. …”
Get full text

Cooperative cellular wireless networks / by Hossain, Ekram, 1971-, Kim, Tong-in, 1958-, Bhargava, Vijay K., 1948-

Editorial introduction to J.UCS special issue Challenges for Smart Environments – Human-Centered Computing, Data Science, and Ambient Intelligence I by Nelson Baloian, José Pino

“…In view of the complexity of contemporary neural network architectures and models with millions of parameters they derive, one of such challenges is related to the concept of explainability of the machine learning models. …”
Get full text

Adaptive neural networks for edge intelligence by Kong, Hao

“…Dynamic image cropping and compound shrinking together constitute a multi-dimensional CNN compression framework, which is able to comprehensively reduce the computational redundancy in both input images and neural network architectures, thereby improving the inference efficiency of CNNs. …”
Get full text