Recent advances in convolutional neural networks
Jiuxiang Gu,Zhenhua Wang,Jason Kuen,Lianyang Ma,Amir Shahroudy,Bing Shuai,Ting Liu,Xingxing Wang,Gang Wang,Jianfei Cai,Tsuhan Chen +10 more
TLDR
A broad survey of the recent advances in convolutional neural networks can be found in this article, where the authors discuss the improvements of CNN on different aspects, namely, layer design, activation function, loss function, regularization, optimization and fast computation.About:
This article is published in Pattern Recognition.The article was published on 2018-05-01 and is currently open access. It has received 3125 citations till now. The article focuses on the topics: Deep learning & Convolutional neural network.read more
Citations
More filters
Journal ArticleDOI
A federated calibration scheme for convolutional neural networks: Models, applications and challenges
TL;DR: In this article , the authors give a definite audit of different deep arrangements and models featuring attributes of a specific convolutional neural network model and conclude the significant challenges associated with Spatial Exploitation based Convolutional Neural Networks (SEN), Depth Based CNN, Multi-Path based CNN, and width based CNN architectures.
Posted Content
Predicting Distresses using Deep Learning of Text Segments in Annual Reports
TL;DR: In this paper, a model consisting of a convolutional recurrent neural network (RNN) was proposed to learn a descriptive representation of the text that is suited for corporate distress prediction.
Journal ArticleDOI
Gas identification with drift counteraction for electronic noses using augmented convolutional neural network
TL;DR: Wang et al. as discussed by the authors proposed a new pattern recognition approach, namely augmented convolutional neural network (ACNN), to solve a gas discrimination problem over an extended period with high accuracy rates.
Journal ArticleDOI
A novel robust algorithm for position and orientation detection based on cascaded deep neural network
TL;DR: The method of a cascade of convolution networks is proposed which results in high precision pose estimates and possesses a greatly improved accuracy and recognition rate compared with the traditional algorithm.
Journal ArticleDOI
Deep learning-based reconstruction of the structure of heterogeneous composites from their temperature fields
TL;DR: A data-driven deep learning model is built to predict the heterogeneous distribution of circle-shaped fillers in two-dimensional thermal composites using the temperature field in the composite as an input.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.