Search
Now showing items 1601-1610 of 2226
Hierarchical mixtures of generators for adversarial learning
Generative adversarial networks (GANs) are deep neural networks that allow us to sample from an arbitrary probability distribution without explicitly estimating the distribution. There is a generator that takes a latent ...
Weight update skipping: Reducing training time for artificial neural networks
(IEEE, 2021-12)
Artificial Neural Networks (ANNs) are known as state-of-the-art techniques in Machine Learning (ML) and have achieved outstanding results in data-intensive applications, such as recognition, classification, and segmentation. ...
Development of an aerial interface for extraction of the electrodynamic fingerprints of the single-photon detectors
(Wiley, 2021-12)
In this study, a novel structure of semi array of antipodal Vivaldi antenna is designed to extract the RF radiations from the single-photon detectors in a quantum key distribution system. The proposed antenna covers a ...
Comprehensive study on UAV-based FSO links for high-speed train backhauling
(The Optical Society, 2021-09-20)
In this paper, we introduce the idea of using unmanned aerial vehicle (UAV)-based free-space optical communication systems to backhaul high-speed trains. We introduce a composite channel model that includes effects of both ...
Synthetic jet cooling technology for electronics thermal management - A critical review
(IEEE, 2021-08)
Effective removal of excess heat from electronics equipment is the key to its intended functionality. A Defense Advanced Research Projects Agency (DARPA) hard problem is proposed in microtechnologies for the air-cooled ...
Misclassification risk and uncertainty quantification in deep classifiers
(IEEE, 2021)
In this paper, we propose risk-calibrated evidential deep classifiers to reduce the costs associated with classification errors. We use two main approaches. The first is to develop methods to quantify the uncertainty of a ...
Learning system dynamics via deep recurrent and conditional neural systems
(IEEE, 2021)
Although there are various mathematical methods for modeling system dynamics, more general solutions can be achieved using deep learning based on data. Alternative deep learning methods are presented in parallel with the ...
Numerical analysis of segmental tunnel linings - Use of the beam-spring and solid-interface methods
(Techno-Press (테크노프레스), 2022-04-16)
The effect of segmental joints is one of main importance for the segmental lining design when tunnels are excavated by a mechanized process. In this paper, segmental tunnel linings are analyzed by two numerical methods, ...
Soil liquefaction-induced uplift of buried pipes in sand-granulated-rubber mixture: Numerical modeling
(Elsevier, 2022-03)
The significant uplift of buried pipes observed during recent earthquakes has showed the need for further research in remediation methods for soil liquefaction. Sand-granulated rubber mixture is reported as a new soil ...
Design and development of a durable series elastic actuator with an optimized spring topology
(Sage, 2021-12)
This paper aims to present the integrated design, development, and testing procedures for a state-of-the-art torsion-based series elastic actuator that could be reliably employed for long-term use in force-controlled robot ...
Share this page