Results 311 to 320 of about 1,718,101 (355)

Face recognition: a convolutional neural-network approach

IEEE Transactions on Neural Networks, 1997
S Lawrence, C Lee Giles, Ah Chung Tsoi
exaly   +2 more sources

Accelerating the Super-Resolution Convolutional Neural Network

European Conference on Computer Vision, 2016
As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) [1, 2] has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However,
Chao Dong, Chen Change Loy, Xiaoou Tang
semanticscholar   +1 more source

Factorized Convolutional Neural Networks

2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017
In this paper, we propose to factorize the convolutional layer to reduce its computation. The 3D convolution operation in a convolutional layer can be considered as performing spatial convolution in each channel and linear projection across channels simultaneously.
Wang, Min, Liu, Baoyuan, Foroosh, Hassan
openaire   +3 more sources

ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars

International Symposium on Computer Architecture, 2016
A number of recent efforts have attempted to design accelerators for popular machine learning algorithms, such as those involving convolutional and deep neural networks (CNNs and DNNs).
A. Shafiee, Anirban Nag, N. Muralimanohar, R. Balasubramonian, J. Strachan, Miao Hu, R. S. Williams, Vivek Srikumar   +7 more
semanticscholar   +1 more source

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

European Conference on Computer Vision, 2016
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32\(\times \) memory saving.
Mohammad Rastegari, Vicente Ordonez, J. Redmon, Ali Farhadi   +3 more
semanticscholar   +1 more source

A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method

IEEE transactions on industrial electronics (1982. Print), 2018
Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis becomes a hot topic. However, the traditional
Long Wen, Xinyu Li, Liang Gao, Yuyan Zhang   +3 more
semanticscholar   +1 more source

Attentiondrop for Convolutional Neural Networks

2019 IEEE International Conference on Multimedia and Expo (ICME), 2019
Dropout has been widely used in fully connected networks but becomes less effective for convolutional neural networks (CNNs), since the spatially correlated features still allow dropped information to flow through the network. To make dropout more practical for CNNs, structured dropout methods have been recently proposed by dropping regions with fixed ...
Zhihao Ouyang, Yan Feng, Zihao He, Tianbo Hao, Tao Dai 0001, Shu-Tao Xia   +5 more
openaire   +1 more source

Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals

Comput. Biol. Medicine, 2017
An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain.
U. R. Acharya, U. R. Acharya, Shu Lih Oh, Yuki Hagiwara, J. Tan, H. Adeli   +5 more
semanticscholar   +1 more source

Convolutional Neural Network

Programming with TensorFlow, 2020
Machine learning is the study of algorithms and models for computing systems to do tasks based on pattern identification and inference. When it is difficult or infeasible to develop an algorithm to do a particular task, machine learning algorithms can ...
M. Véstias
semanticscholar   +1 more source

Denoising Convolutional Neural Network

2015 IEEE International Conference on Information and Automation, 2015
Convolutional Neural Network (CNN) is a kind of deep artificial neural network. CNN has kinds of merits, such as multidimensional data input, and fewer parameters. However, the network always has the problem of overfitting due to lots of connection in the full connection layer.
Qingyang Xu, Chengjin Zhang, Li Zhang 0043   +2 more
openaire   +1 more source