Results 41 to 50 of about 4,971 (264)
Augmenting Paraphrase Generation with Syntax Information Using Graph Convolutional Networks
Entropy, 2021 Paraphrase generation is an important yet challenging task in natural language processing. Neural network-based approaches have achieved remarkable success in sequence-to-sequence learning.
Xiaoqiang Chi, Yang Xiang
doaj +1 more source
Seesaw-Net: Convolution Neural Network With Uneven Group Convolution
CoRR, 2019 In this paper, we are interested in boosting the representation capability of convolution neural networks which utilizing the inverted residual structure. Based on the success of Inverted Residual structure[Sandler et al. 2018] and Interleaved Low-Rank Group Convolutions[Sun et al.
openaire +2 more sources
Simplicial 2-Complex Convolutional Neural Nets
, 2020 Recently, neural network architectures have been developed to accommodate when the data has the structure of a graph or, more generally, a hypergraph. While useful, graph structures can be potentially limiting. Hypergraph structures in general do not account for higher order relations between their hyperedges. Simplicial complexes offer a middle ground,
Bunch, Eric +3 more
openaire +2 more sources
Efficient Training of Convolutional Neural Nets on Large Distributed Systems [PDF]
2018 IEEE International Conference on Cluster Computing (CLUSTER), 2018 Deep Neural Networks (DNNs) have achieved im- pressive accuracy in many application domains including im- age classification. Training of DNNs is an extremely compute- intensive process and is solved using variants of the stochastic gradient descent (SGD) algorithm. A lot of recent research has focussed on improving the performance of DNN training.
Dheeraj Sreedhar +4 more
openaire +2 more sources
Advanced Engineering Materials, EarlyView.Low‐voltage FIB‐SEM tomography combined with a image preprocessing pipeline improves phase contrast and enables reliable machine‐learning segmentation of conductive networks in lithium‐ion battery electrodes. Structural descriptors are extracted from segmented images, done semimanually and automated, and compared.
Lisa Beran +6 more
wiley +1 more source
SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation
IET Image Processing, 2023 Medical images exhibit multi‐granularity and high obscurity along boundaries. As representative work, the U‐Net and its variants exhibit two shortcomings on medical image segmentation: (a) they expand the range of reception fields by applying addition or
Shaofan Wang +3 more
doaj +1 more source
Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks [PDF]
Communications in Computational Physics, 2020 Deep networks, especially convolutional neural networks (CNNs), have been successfully applied in various areas of machine learning as well as to challenging problems in other scientific and engineering fields. This paper introduces Butterfly-net, a low-complexity CNN with structured and sparse cross-channel connections, together with a Butterfly ...
Li, Y, Cheng, X, Lu, J
openaire +2 more sources
Advanced Engineering Materials, EarlyView.This study applies machine learning regression to predict chromium layer thickness in decorative trivalent chromium electroplating, using 441 experiments from laboratory‐scale (1L) and pilot‐scale (14L) setups. Tree‐based models, particularly CatBoost, outperformed linear regression by capturing nonlinear parameter interactions (R2$R^2$ up to 0.77 ...
Christoph Baumer +4 more
wiley +1 more source
Cells, 2020 Over a decade ago, the formation of neutrophil extracellular traps (NETs) was described as a novel mechanism employed by neutrophils to tackle infections.
Aneta Manda-Handzlik +4 more
doaj +1 more source