Results 11 to 20 of about 591 (120)
A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks
Journal of Statistical Planning and InferenceTo investigate neural network parameters, it is easier to study the distribution of parameters than to study the parameters in each neuron. The ridgelet transform is a pseudo-inverse operator that maps a given function $f$ to the parameter distribution $\
Ikeda, Masahiro +2 more
core +2 more sources
Fusion High-and-Low-Level Features via Ridgelet and Convolutional Neural Networks for Very High-Resolution Remote Sensing Imagery Classification [PDF]
IEEE Access, 2019 Ridgelet can theoretically approximate low-level image features, and the ridgelet filter is constructed independently of the training sample, but it usually requires to preset a lot of parameters to achieve an ideal representation of complex scenes.
Zhifeng Zheng
exaly +3 more sources
Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups
Advances in Neural Information Processing Systems 35, 2022 We show the universality of depth-2 group convolutional neural networks (GCNNs) in a unified and constructive manner based on the ridgelet theory. Despite widespread use in applications, the approximation property of (G)CNNs has not been well investigated. The universality of (G)CNNs has been shown since the late 2010s. Yet, our understanding on how (G)
Sho Sonoda +2 more
openaire +3 more sources
IEEE Access, 2021 Renewable energy (RE) generation levels are increasing in modern power systems at a fast rate due to their advantages of clean and non-exhaustible nature of energy.
Nagendra Kumar Swarnkar +3 more
doaj +1 more source
Energy Reports, 2022 Modeling and forecasting electricity consumption (EC) help industry managers make better strategic decisions. In this study, a hybrid approach for predicting EC is proposed which first EC is decomposed into approximate and detail parts based on wavelet ...
Alireza Saranj, Mehdi Zolfaghari
doaj +1 more source
Multivariable passive method for detection of islanding events in renewable energy based power grids
IET Renewable Power Generation, 2022 Penetration of distributed generation resources (DGR) in power grid is rapidly increasing to meet future energy demand efficiently. It helps in mitigating the problems of high carbon emission, green house effect, and increased cost of oil and natural ...
Nagendra Kumar Swarnkar +3 more
doaj +1 more source
J. Mach. Learn. Res., 2020 Bayesian neural networks attempt to combine the strong predictive performance of neural networks with formal quantification of uncertainty associated with the predictive output in the Bayesian framework. However, it remains unclear how to endow the parameters of the network with a prior distribution that is meaningful when lifted into the output space ...
Matsubara T, Oates CJ, Briol F-X
openaire +5 more sources
The aceToolbox: low-level audiovisual feature extraction for retrieval and classification [PDF]
, 2005 In this paper we present an overview of a software platform that has been developed within the aceMedia project, termed the aceToolbox, that provides global and local lowlevel feature extraction from audio-visual content.
Adamek, Tomasz +4 more
core +2 more sources
Signature of a Cosmic String Wake at $z=3$
, 2020 In this paper, we describe the results of N-body simulation runs, which include a cosmic string wake of tension $G\mu= 4 \times 10^{-8}$ on top of the usual $\Lambda CDM$ fluctuations. To obtain a higher resolution of the wake in the simulations compared
da Cunha, Disrael Camargo Neves
core +1 more source
Face detection in profile views using fast discrete curvelet transform (FDCT) and support vector machine (SVM) [PDF]
, 2016 Human face detection is an indispensable component in face processing applications, including automatic face recognition, security surveillance, facial expression recognition, and the like.
Abu-Bakar, A. R., Muhammad, B.
core +1 more source