Zobrazeno 1 - 10
of 75
pro vyhledávání: '"Perambur S. Neelakanta"'
Autor:
Perambur S. Neelakanta, Aziz U. Noori
Publikováno v:
NETNOMICS: Economic Research and Electronic Networking. 22:85-113
Publikováno v:
Transactions on Machine Learning and Artificial Intelligence. 10:27-45
In the contexts of deep learning (DL) considered in artificial intelligence (AI) efforts, relevant machine learning (ML) algorithms adopted refer to using a class of deep artificial neural network (ANN) that supports a learning process exercised with
Publikováno v:
Transactions on Networks and Communications. 9:1-22
The objective of this study is to deduce signal-to-noise ratio (SNR) based loglikelihood function involved in detecting low-observable targets (LoTs) including drones Illuminated by a low probability of intercept (LPI) radar operating in littoral reg
Publikováno v:
Transactions on Networks and Communications. 9:1-35
Facilitating newer bands of ‘unused’ segments (windows) of RF spectrum falling in the mm-wave range (above 30+ GHz) and seeking usable stretches across unallocated THz spectrum, could viably be considered for Multiple Input Multiple Output (MIMO)
Publikováno v:
INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY. 18:7431-7439
This study refers to developing an electric-power distribution system with optimal/suboptimal load-sharing in the complex and expanding metro power-grid infrastructure. That is, the relevant exercise is to indicate a smart forecasting strategy on opt
Publikováno v:
INFORMATION-THEORETIC ASPECTS of NEURAL NETWORKS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c1fd9b14a8e32245f27061e46440752e
https://doi.org/10.1201/9781003067931-8
https://doi.org/10.1201/9781003067931-8
Publikováno v:
INFORMATION-THEORETIC ASPECTS of NEURAL NETWORKS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::820373b2939614cc05d4f0659e7a04be
https://doi.org/10.1201/9781003067931-6
https://doi.org/10.1201/9781003067931-6
Publikováno v:
INFORMATION-THEORETIC ASPECTS of NEURAL NETWORKS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b79b2383e42f746bdf09f18ab01d2043
https://doi.org/10.1201/9781003067931-2
https://doi.org/10.1201/9781003067931-2
Publikováno v:
INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY. 17:7126-7132
Proposed in this paper is a novel fast-convergence algorithm applied to neural networks (ANNs) with a learning rate based on the eigenvalues of the associated Hessian matrix of the input data. That is, the learning rate applied to the backpropagation