Home »
Academic Articles & Research Papers
Showing 20 of 4,465 academic articles
Nachimuthu Karunanithi, Darrell Whitley, Yashwant K. Malaiya • IEEE Software
(1992)
It is shown that neural network reliability growth models have a significant advantage over analytic models in that they require only failure history as input and not assumptions about either the development environment or external paramete...
OPENALEX
DOI: https://doi.org/10.1109/52.143107
Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler et al. • arXiv (Cornell University)
(2018)
Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with $100\%$ accuracy. In this work, we present properties of neural networks that complement this aspect of expressivity. ...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1806.08734
Pooja Jain, Makarand Chintamani Deo • Ships and Offshore Structures
(2005)
The soft computing technique of neural network is being extensively used across all disciplines of ocean engineering, namely, offshore, coastal, and deep-ocean engineering including marine engineering. This paper takes a stock of the resear...
OPENALEX
DOI: https://doi.org/10.1533/saos.2004.0005
Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann • arXiv (Cornell University)
(2018)
Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par with Euclidean geomet...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1805.09112
Donald F. Specht • IEEE Transactions on Neural Networks
(1991)
A memory-based network that provides estimates of continuous variables and converges to the underlying (linear or nonlinear) regression surface is described. The general regression neural network (GRNN) is a one-pass learning algorithm with...
OPENALEX
DOI: https://doi.org/10.1109/72.97934
Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele et al. • arXiv (Cornell University)
(2018)
In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specialists can understand...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1808.04260
Nicholas Carlini, David Wagner • IEEE Symposium on Security and Privacy (S&P)
(2017)
Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input x and any target classification t, it is possible to find a new input x'...
OPENALEX
Open Access
DOI: https://doi.org/10.1109/sp.2017.49
J. Lee, Ronald C. Weger, S.K. Sengupta, Ronald M. Welch • IEEE Transactions on Geoscience and Remote Sensing
(1990)
It is shown that, using high-spatial-resolution data, very high cloud classification accuracies can be obtained with a neural network approach. A texture-based neural network classifier using only single-channel visible Landsat MSS imagery ...
OPENALEX
DOI: https://doi.org/10.1109/36.58972
Timothy X. Brown • IEEE Communications Magazine
(1989)
The author argues that a strong impetus for using neural networks is that they provide a framework for designing massively parallel machines. He notes that the highly interconnected architecture of switching networks suggests similarities t...
OPENALEX
DOI: https://doi.org/10.1109/35.41403
Manish Kumar Mishra, Monika Srivastava • International Conference on Advances in Engineering & Technology Research
(2014)
In this paper, An Artificial Neural Network or ANN, its various characteristics and business applications. In this paper also show that “what are neural networks” and “Why they are so important in today's Artificial intelligence?” Because v...
OPENALEX
DOI: https://doi.org/10.1109/icaetr.2014.7012785
S. Reynold Chu, Rahmat A. Shoureshi, Manoel Fernando Tenorio • IEEE Control Systems Magazine
(1990)
Two approaches are presented for utilization of neural networks in identification of dynamical systems. In the first approach, a Hopfield network is used to implement a least-squares estimation for time-varying and time-invariant systems. T...
OPENALEX
DOI: https://doi.org/10.1109/37.55121
Mike Schuster, Kuldip K. Paliwal • IEEE Transactions on Signal Processing
(1997)
In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up to a preset future f...
OPENALEX
DOI: https://doi.org/10.1109/78.650093
J. T. Gene Hwang, Aidong Adam Ding • Journal of the American Statistical Association
(1997)
The artificial neural network (ANN) is becoming a very popular model for engineering and scientific applications. Inspired by brain architecture, artificial neural networks represent a class of nonlinear models capable of learning from data...
OPENALEX
DOI: https://doi.org/10.1080/01621459.1997.10474027
Bing Cheng, D. Michael Titterington • Statistical Science
(1994)
This paper informs a statistical readership about Artificial Neural Networks (ANNs), points out some of the links with statistical methodology and encourages cross-disciplinary research in the directions most likely to bear fruit. The areas...
OPENALEX
Open Access
DOI: https://doi.org/10.1214/ss/1177010638
Miles Cranmer, Sam Greydanus, Stephan Hoyer, Peter Battaglia et al. • arXiv (Cornell University)
(2020)
Accurate models of the world are built upon notions of its underlying symmetries. In physics, these symmetries correspond to conservation laws, such as for energy and momentum. Yet even though neural network models see increasing use in the...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.2003.04630
Daniel J. Amit, Hanoch Gutfreund, Haim Sompolinsky • Physical Review A
(1985)
Two dynamical models, proposed by Hopfield and Little to account for the collective behavior of neural networks, are analyzed. The long-time behavior of these models is governed by the statistical mechanics of infinite-range Ising spin-glas...
OPENALEX
DOI: https://doi.org/10.1103/physreva.32.1007
Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner et al. • IEEE Transactions on Neural Networks
(2008)
Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper,...
OPENALEX
Open Access
DOI: https://doi.org/10.1109/tnn.2008.2005605
Chris Bishop • Choice Reviews Online
(1994)
From the Publisher:
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basic concepts, the book examines techniques for modelling probabi...
OPENALEX
DOI: https://doi.org/10.5860/choice.31-5500
Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals • arXiv (Cornell University)
(2014)
We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In ...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1409.2329
José M. Benítez, Juan Luis Castro, Ignacio Requena • IEEE Transactions on Neural Networks
(1997)
Artificial neural networks are efficient computing models which have shown their strengths in solving hard problems in artificial intelligence. They have also been shown to be universal approximators. Notwithstanding, one of the major criti...
OPENALEX
DOI: https://doi.org/10.1109/72.623216