Reset
Showing 20 of 3,743 academic articles

Neural Networks in Civil Engineering: 1989–2000

Hojjat Adeli • Computer-Aided Civil and Infrastructure Engineering (2001)

The first journal article on neural network application in civil/structural engineering was published by in this journal in 1989. This article reviews neural network articles published in archival research journals since then. The emphasis ...

OPENALEX cc-by-nc-nd DOI: https://doi.org/10.1111/0885-9507.00219

Neural Networks in Applied Statistics

Hal S. Stern • Technometrics (1996)

Artificial neural networks are computer algorithms or computer programs derived in part from attempts to model the activity of nerve cells. They have been applied to pattern recognition, classification, and optimization problems in the phys...

OPENALEX DOI: https://doi.org/10.1080/00401706.1996.10484497

Understanding Neural Networks as Statistical Tools

Brad Warner, Manavendra Misra • The American Statistician (1996)

Neural networks have received a great deal of attention over the last few years. They are being used in the areas of prediction and classification, areas where regression models and other related statistical techniques have traditionally be...

OPENALEX DOI: https://doi.org/10.1080/00031305.1996.10473554

Introduction to artificial neural networks

Robert E. Uhrig • Annual Conference of the IEEE Industrial Electronics Society (IECON) (2002)

A neural network is a data processing system consisting of a large number of simple, highly interconnected processing elements in an architecture inspired by the structure of the cerebral cortex portion of the brain. Hence, neural networks ...

OPENALEX DOI: https://doi.org/10.1109/iecon.1995.483329

Intriguing properties of neural networks

Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna et al. • arXiv (Cornell University) (2013)

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn uninterpr...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1312.6199

Hamiltonian Neural Networks

Sam Greydanus, Misko Dzamba, Jason Yosinski • arXiv (Cornell University) (2019)

Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models th...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1906.01563

A neural network model for survival data

David Faraggi, Richard M Simon • Statistics in Medicine (1995)

Neural networks have received considerable attention recently, mostly by non-statisticians. They are considered by many to be very promising tools for classification and prediction. In this paper we present an approach to modelling censored...

OPENALEX DOI: https://doi.org/10.1002/sim.4780140108

Hypergraph Neural Networks

Yifan Feng, Haoxuan You, Zizhao Zhang, Rongrong Ji et al. • Proceedings of the AAAI Conference on Artificial Intelligence (2019)

In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph structure. Confronting the challenges of learning representation for comp...

OPENALEX Open Access DOI: https://doi.org/10.1609/aaai.v33i01.33013558

Applications of Neural Networks in Electromagnetics

Christos Christodoulou, Michael Georgiopoulos • CERN Document Server (European Organization for Nuclear Research) (2001)

From the Book: Since the early 1990s, a plethora of electromagnetic problems have been tackled using neural networks, some more successfully than others. Because neural networks and electromagnetics are two different scientific fields, not...

OPENALEX

An Introduction to Convolutional Neural Networks

Aarush Saxena • International Journal for Research in Applied Science and Engineering Technology (2022)

Abstract: The field of machine learning has taken a dramatic twist in re- cent times, with the rise of the Artificial Neural Network (ANN). These biologically inspired computational models can far exceed the per- performance of previous for...

OPENALEX Open Access DOI: https://doi.org/10.22214/ijraset.2022.47789

Pulsed Neural Networks

• The MIT Press eBooks (1998)

Most practical applications of artificial neural networks are based on a computational model involving the propagation of continuous variables from one processing unit to the next. In recent years, data from neurobiological experiments have...

OPENALEX DOI: https://doi.org/10.7551/mitpress/5704.001.0001

cuDNN: Efficient Primitives for Deep Learning

Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Cohen, Jonathan et al. • arXiv (Cornell University) (2014)

We present a library of efficient implementations of deep learning primitives. Deep learning workloads are computationally intensive, and optimizing their kernels is difficult and time-consuming. As parallel architectures evolve, kernels mu...

OPENALEX Open Access DOI: https://doi.org/10.48550/arxiv.1410.0759

PG-MACO Optimization Method for Ship Pipeline Layout

LIN Yan, JIN Tingyu, YANG Yuchao • Shanghai Jiaotong Daxue xuebao (2024)

Aimed at the problem of low efficiency of ship pipeline design, an optimization method of pipeline layout is proposed. An optimization mathematical model is established by comprehensively considering the engineering background of safety, ec...

DOAJ Open Access (DOAJ) DOI: 10.16183/j.cnki.jsjtu.2022.508

EdgeAIGC: Model caching and resource allocation for edge artificial intelligence generated content

Wu Wen, Yibin Huang, Xinxin Zhao, Peiying Zhang et al. • Digital Communications and Networks (2025)

With the rapid development of generative artificial intelligence technology, the traditional cloud-based centralized model training and inference face significant limitations due to high transmission latency and costs, which restrict user-s...

DOAJ Open Access (DOAJ) DOI: 10.1016/j.dcan.2025.07.003