Results 11 to 20 of about 52,085 (312)
Entangled q-convolutional neural nets
Machine Learning: Science and Technology, 2021 We introduce a machine learning model, the q-CNN model, sharing key features with convolutional neural networks and admitting a tensor network description. As examples, we apply q-CNN to the MNIST and Fashion MNIST classification tasks. We explain how the network associates a quantum state to each classification label, and study the entanglement ...
Vassilis Anagiannis, Miranda C. N. Cheng
openalex +5 more sources
Fully convolutional neural nets in-the-wild [PDF]
Remote Sensing Letters, 2020 The ground breaking performance of fully convolutional neural nets (FCNs) for semantic segmentation tasks has yet to be achieved for landcover classification, partly because a lack of suitable trai...
Daniel M. Simms
openalex +4 more sources
Communication-Optimal Convolutional Neural Nets [PDF]
, 2018 Efficiently executing convolutional neural nets (CNNs) is important in many machine-learning tasks. Since the cost of moving a word of data, either between levels of a memory hierarchy or between processors over a network, is much higher than the cost of an arithmetic operation, minimizing data movement is critical to performance optimization.
James Demmel, Grace Dinh
openalex +3 more sources
Convolutional neural nets in chemical engineering: Foundations, computations, and applications [PDF]
AIChE Journal, 2021 AbstractIn this article, we review the mathematical foundations of convolutional neural nets (CNNs) with the goals of: (i) highlighting connections with techniques from statistics, signal processing, linear algebra, differential equations, and optimization, (ii) demystifying underlying computations, and (iii) identifying new types of applications. CNNs
Shengli Jiang, Víctor M. Zavala
openalex +4 more sources
Inferring depth contours from sidescan sonar using convolutional neural nets [PDF]
IET Radar, Sonar & Navigation, 2019 Sidescan sonar images are 2D representations of the seabed. The pixel location encodes distance from the sonar and along track coordinate. Thus one dimension is lacking for generating bathymetric maps from sidescan. The intensities of the return signals do, however, contain some information about this missing dimension.
Yiping Xie, Nils Bore, John Folkesson
openalex +3 more sources
Network Inversion of Convolutional Neural Nets [PDF]
Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability and reliability, especially in safety-critical scenarios.
Pirzada Suhail, Amit Sethi
openalex +3 more sources
Convex Relaxations of Convolutional Neural Nets [PDF]
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019 We propose convex relaxations for convolutional neural nets with one hidden layer where the output weights are fixed. For convex activation functions such as rectified linear units, the relaxations are convex second order cone programs which can be solved very efficiently.
Bartan, Burak, Pilanci, Mert
openaire +2 more sources
Rumour Detection Based on Graph Convolutional Neural Net [PDF]
IEEE Access, 2021 Rumor detection is an important research topic in social networks, and lots of rumor detection models are proposed in recent years. For the rumor detection task, structural information in a conversation can be used to extract effective features. However, many existing rumor detection models focus on local structural features while the global structural
Na Bai +3 more
openaire +2 more sources
LiteDEKR: End‐to‐end lite 2D human pose estimation network
IET Image Processing, 2023 The 2D human pose estimation plays an important role in human‐computer interaction and action recognition. Although the method based on high‐resolution network has superior performance, there is still room for improvement in terms of speed and ...
Xueqiang Lv +5 more
doaj +1 more source
Ph-Net: Parallelepiped Microstructure Homogenization Via 3d Convolutional Neural Networks
SSRN Electronic Journal, 2022 Microstructures are attracting academic and industrial interests with the rapid development of additive manufacturing. The numerical homogenization method has been well studied for analyzing mechanical behaviors of microstructures; however, it is too time-consuming to be applied to online computing or applications requiring high-frequency calling, e.g.,
Hao Peng +5 more
openaire +2 more sources