Results 11 to 20 of about 534,506 (301)
3rd International Conference on Electromechanical Control Technology and Transportation, 2018 Convolutional neural networks are designed to work with grid-structured inputs, which have strong spatial dependencies in local regions of the grid. The most obvious example of grid-structured data is a 2-dimensional image. This type of data also exhibits spatial dependencies, because adjacent spatial locations in an image often have similar color ...
Mathew Salvaris +2 more
+12 more sources
Pansharpening by Convolutional Neural Networks [PDF]
Remote Sensing, 2016 A new pansharpening method is proposed, based on convolutional neural networks. We adapt a simple and effective three-layer architecture recently proposed for super-resolution to the pansharpening problem. Moreover, to improve performance without increasing complexity, we augment the input by including several maps of nonlinear radiometric indices ...
MASI, GIUSEPPE +3 more
openaire +4 more sources
Quantum convolutional neural networks [PDF]
Nature Physics, 2019 12 pages, 11 figures. v2: New application to optimizing quantum error correction codes, added sample complexity analysis, more details for experimental realizations, and other minor ...
Soonwon Choi +3 more
openaire +5 more sources
Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model
Journal of Harbin University of Science and Technology, 2020 Aiming at the problem that some offline handwritten Chinese characters are similar in shape and it is difficult to extract the feature of characters and the recognition is not accurate, a convolutional neural network and deep belief network fusion model ...
LI Lanying, ZHOU Zhigang, CHEN Deyun
doaj +1 more source
Parallel accelerator design for convolutional neural networks based on FPGA
Dianzi Jishu Yingyong, 2021 In recent years, convolutional neural network plays an increasingly important role in many fields. However, power consumption and speed are the main factors limiting its application.
Wang Ting, Chen Binyue, Zhang Fuhai
doaj +1 more source
Orthogonal Convolutional Neural Networks [PDF]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonality on convolutional filters. We develop an efficient approach to impose filter orthogonality on a convolutional layer based on the doubly block-Toeplitz matrix ...
Rudrasis Chakraborty +3 more
openaire +3 more sources
Contextual Convolutional Neural Networks [PDF]
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021 We propose contextual convolution (CoConv) for visual recognition. CoConv is a direct replacement of the standard convolution, which is the core component of convolutional neural networks. CoConv is implicitly equipped with the capability of incorporating contextual information while maintaining a similar number of parameters and computational cost ...
Radu Tudor Ionescu +2 more
openaire +2 more sources
Airborne Network Traffic Identification Method under Small Training Samples
Xibei Gongye Daxue Xuebao, 2020 Due to the high cost and difficulty of traffic data set acquisition and the high time sensitivity of traffic distribution, the machine learning-based traffic identification method is difficult to be applied in airborne network environment. Aiming at this
doaj +1 more source
Biomolecules, 2021 Identifying localization of proteins and their specific subpopulations associated with certain cellular compartments is crucial for understanding protein function and interactions with other macromolecules. Fluorescence microscopy is a powerful method to
Kaisa Liimatainen +3 more
doaj +1 more source
Canonical convolutional neural networks
2022 International Joint Conference on Neural Networks (IJCNN), 2022 We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode ...
Veeramacheneni, Lokesh +3 more
openaire +2 more sources