Results 41 to 50 of about 52,973 (279)

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

Adversarial nets with perceptual losses for text-to-image synthesis

, 2017
Recent approaches in generative adversarial networks (GANs) can automatically synthesize realistic images from descriptive text. Despite the overall fair quality, the generated images often expose visible flaws that lack structural definition for an ...
Cha, Miriam, Gwon, Youngjune, Kung, H. T.   +2 more
core   +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, You, Qian, Fung, Glenn, Singh, Vikas   +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, Vaibhav Saxena, Yogish Sabharwal, Ashish Verma 0001, Sameer Kumar 0001   +4 more
openaire   +2 more sources

Prediction of Surface Topography Parameters in Direct Laser Interference Patterning of Stainless Steel Using Infrared Monitoring and Convolutional Neural Networks

Advanced Engineering Materials, EarlyView.
This study presents an infrared monitoring approach for direct laser interference patterning (DLIP) combined with a convolutional neural network (CNN). Thermal emission data captured during structuring are used to predict surface topography parameters.
Lukas Olawsky, Marcelo Sallese, Leander Kläber, Clemens Kuhn, Keming Du, Andrés Fabián Lasagni   +5 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, Yukun Liu, Yanfeng Sun, Baocai Yin   +3 more
doaj   +1 more source

Improving neural networks by preventing co-adaptation of feature detectors [PDF]

, 2012
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case.
Hinton, Geoffrey E., Krizhevsky, Alex, Salakhutdinov, Ruslan R., Srivastava, Nitish, Sutskever, Ilya   +4 more
core   +1 more source

Monocular Object Instance Segmentation and Depth Ordering with CNNs

, 2015
In this paper we tackle the problem of instance-level segmentation and depth ordering from a single monocular image. Towards this goal, we take advantage of convolutional neural nets and train them to directly predict instance-level segmentations where ...
Fidler, Sanja, Schwing, Alexander G., Urtasun, Raquel, Zhang, Ziyu   +3 more
core   +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