Algorithm unrolling: Interpretable, efficient deep learning for signal and image processing
Deep neural networks provide unprecedented performance gains in many real-world
problems in signal and image processing. Despite these gains, the future development and …
problems in signal and image processing. Despite these gains, the future development and …
A transfer learning method with deep residual network for pediatric pneumonia diagnosis
G Liang, L Zheng - Computer methods and programs in biomedicine, 2020 - Elsevier
Abstract Background and Objective Computer aided diagnosis systems based on deep
learning and medical imaging is increasingly becoming research hotspots. At the moment …
learning and medical imaging is increasingly becoming research hotspots. At the moment …
Variational continual learning
This paper develops variational continual learning (VCL), a simple but general framework
for continual learning that fuses online variational inference (VI) and recent advances in …
for continual learning that fuses online variational inference (VI) and recent advances in …
[HTML][HTML] Intelligent estimation: A review of theory, applications, and recent advances
Recent developments in the field of deep learning have led to the widespread integration of
artificial neural networks in various domains of application. Prominent contemporary artificial …
artificial neural networks in various domains of application. Prominent contemporary artificial …
Roadtracer: Automatic extraction of road networks from aerial images
Mapping road networks is currently both expensive and labor-intensive. High-resolution
aerial imagery provides a promising avenue to automatically infer a road network. Prior work …
aerial imagery provides a promising avenue to automatically infer a road network. Prior work …
New insights and perspectives on the natural gradient method
J Martens - Journal of Machine Learning Research, 2020 - jmlr.org
Natural gradient descent is an optimization method traditionally motivated from the
perspective of information geometry, and works well for many applications as an alternative …
perspective of information geometry, and works well for many applications as an alternative …
Efficient and optimal penetration path planning for stealth unmanned aerial vehicle using minimal radar cross-section tactics and modified A-Star algorithm
Z Zhang, J Jiang, J Wu, X Zhu - ISA transactions, 2023 - Elsevier
Penetration path planning for stealth unmanned aerial vehicles (SUAVs) in the integrated air
defense system (IADS) has been a hot research topic in recent years. The present study …
defense system (IADS) has been a hot research topic in recent years. The present study …
Training feedforward networks with the Marquardt algorithm
MT Hagan, MB Menhaj - IEEE transactions on Neural Networks, 1994 - ieeexplore.ieee.org
The Marquardt algorithm for nonlinear least squares is presented and is incorporated into
the backpropagation algorithm for training feedforward neural networks. The algorithm is …
the backpropagation algorithm for training feedforward neural networks. The algorithm is …
ANFIS: adaptive-network-based fuzzy inference system
JSR Jang - IEEE transactions on systems, man, and …, 1993 - ieeexplore.ieee.org
The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy
inference system) is presented, which is a fuzzy inference system implemented in the …
inference system) is presented, which is a fuzzy inference system implemented in the …
The unscented Kalman filter for nonlinear estimation
EA Wan, R Van Der Merwe - Proceedings of the IEEE 2000 …, 2000 - ieeexplore.ieee.org
This paper points out the flaws in using the extended Kalman filter (EKE) and introduces an
improvement, the unscented Kalman filter (UKF), proposed by Julier and Uhlman (1997). A …
improvement, the unscented Kalman filter (UKF), proposed by Julier and Uhlman (1997). A …