Home »
Academic Articles & Research Papers
Showing 19 of 39 academic articles
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens et al. • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings
(2016)
Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmark...
OPENALEX
DOI: https://doi.org/10.1109/cvpr.2016.308
Hao Huang, G.T.S. Ho, V. Tang, E.W.H. Chow et al. • Journal of Advanced Research
(2026)
Introduction: Crack damage is a significant issue in tunnel environments, requiring efficient and reliable detection to ensure structural integrity. Many existing solutions are computationally expensive, making them unsuitable for the tight...
DOAJ
Open Access (DOAJ)
DOI: 10.1016/j.jare.2025.11.052
Frank R. Burden, David Alan Winkler • Methods in molecular biology
(2008)
Bayesian regularized artificial neural networks (BRANNs) are more robust than standard back-propagation nets and can reduce or eliminate the need for lengthy cross-validation. Bayesian regularization is a mathematical process that converts ...
OPENALEX
DOI: https://doi.org/10.1007/978-1-60327-101-1_3
P. Jagadesh, J. Harshini, D. Arul, Solomon Oyebisi et al. • Discover Civil Engineering
(2026)
Abstract This study predicts the Air Quality Index (AQI) in the Coimbatore region using Artificial Neural Networks (ANN) to enhance air quality management and environmental science. The researchers measured six input variables over a two-ye...
DOAJ
Open Access (DOAJ)
DOI: 10.1007/s44290-026-00423-z
Yao He, Jing Yang, Shaobo Li, Jianjun Hu et al. • Complex & Intelligent Systems
(2024)
Abstract Catastrophic forgetting in neural networks is a common problem, in which neural networks lose information from previous tasks after training on new tasks. Although adopting a regularization method that preferentially retains the pa...
DOAJ
Open Access (DOAJ)
DOI: 10.1007/s40747-024-01350-1
Jiquan Ngiam, Adam Coates, Ahbik Lahiri, Bobby Prochnow et al. • International Conference on Machine Learning
(2011)
The predominant methodology in training deep learning advocates the use of stochastic gradient descent methods (SGDs). Despite its ease of implementation, SGDs are difficult to tune and parallelize. These problems make it challenging to dev...
OPENALEX
Liurong Tao, Haoran Ren, Zhiwei Gu • Remote Sensing
(2023)
Seismic impedance inversion is a vital way of geological interpretation and reservoir investigation from a geophysical perspective. However, it is inevitably an ill-posed problem due to the noise or the band-limited characteristic of seismi...
DOAJ
Open Access (DOAJ)
DOI: 10.3390/rs15040891
Naledi Lenah Adam, Grzegorz Kowalik, Andrew Tyler, Ronald Mooiweer et al. • Frontiers in Cardiovascular Medicine
(2024)
BackgroundSimultaneous multi-slice (SMS) bSSFP imaging enables stress myocardial perfusion imaging with high spatial resolution and increased spatial coverage. Standard parallel imaging techniques (e.g., TGRAPPA) can be used for image recon...
DOAJ
Open Access (DOAJ)
DOI: 10.3389/fcvm.2024.1350345
Andrew J. Reader, Guillaume Corda-D’Incan, Abolfazl Mehranian, Casper O. da Costa-Luis et al. • IEEE Transactions on Radiation and Plasma Medical Sciences
(2020)
This article reviews the use of a subdiscipline of artificial intelligence (AI), deep learning, for the reconstruction of images in positron emission tomography (PET). Deep learning can be used either directly or as a component of conventio...
OPENALEX
Open Access
DOI: https://doi.org/10.1109/trpms.2020.3014786
Peter L. Bartlett, Andrea Montanari A, Alexander Rakhlin • Acta Numerica
(2021)
The remarkable practical success of deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-optimal solutions to non-convex optimization problems, and despite g...
OPENALEX
cc-by
DOI: https://doi.org/10.1017/s0962492921000027
Jan Kukačka, Vladimir Golkov, Daniel Cremers • arXiv (Cornell University)
(2017)
Regularization is one of the crucial ingredients of deep learning, yet the term regularization has various definitions, and regularization methods are often studied separately from each other. In our work we present a systematic, unifying t...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1710.10686
Connor Shorten, Taghi M. Khoshgoftaar, Borko Furht • Journal Of Big Data
(2021)
Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the Data Augmentation training strategy can aid in its development. We begin with the major motifs of Data Augme...
OPENALEX
cc-by
DOI: https://doi.org/10.1186/s40537-021-00492-0
PMC: 8287113
Shaorong Zhang, Shaorong Zhang, Qihui Wang, Benxin Zhang et al. • Frontiers in Neuroscience
(2023)
IntroductionThe time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses signi...
DOAJ
Open Access (DOAJ)
DOI: 10.3389/fnins.2023.1292724
Ian Goodfellow, Yoshua Bengio, Aaron C. Courville • The MIT Press eBooks
(2016)
Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human c...
OPENALEX
DOI: https://doi.org/10.1016/b978-0-12-804291-5.00010-6
Jiuxin Wang, Yutian Luo, Zhengming Yang, Xinli Zhao et al. • Applied Sciences
(2021)
In order to improve the measurement speed and prediction accuracy of unconventional reservoir parameters, the deep neural network (DNN) is used to predict movable fluid percentage of unconventional reservoirs. The Adam optimizer is used in ...
DOAJ
Open Access (DOAJ)
DOI: 10.3390/app11083589
Sun Ping • Materials Research Express
(2026)
Polymer solar cells (PSCs) rely on labor-intensive trial-and-error experiments to optimize power conversion efficiency (PCE), due to complex coupling of molecular electronic properties, blend morphology and fabrication parameters. This work...
DOAJ
Open Access (DOAJ)
DOI: 10.1088/2053-1591/aeaacc
Kevin P. Murphy (2012)
Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict fu...
OPENALEX
Urslla Uchechi Izuazu, Cosmas Ifeanyi Nwakanma, Dong-Seong Kim, Jae Min Lee • Discover Internet of Things
(2025)
Abstract Deep learning-based intrusion detection systems (DL-IDS) have proven effective in detecting cyber threats. However, their vulnerability to adversarial attacks and environmental noise, particularly in industrial settings, limits pra...
DOAJ
Open Access (DOAJ)
DOI: 10.1007/s43926-025-00100-0
Fan Yang, Ping Fan, Xiao-Xiao Li, Xin-Yi Ma • Mathematics
(2019)
In present paper, we deal with a backward diffusion problem for a time-fractional diffusion problem with a nonlinear source in a strip domain. We all know this nonlinear problem is severely ill-posed, i.e., the solution does not depend cont...
DOAJ
Open Access (DOAJ)
DOI: 10.3390/math7090865