Results 281 to 290 of about 203,239 (310)
Some of the next articles are maybe not open access.
Attentiondrop for Convolutional Neural Networks
2019 IEEE International Conference on Multimedia and Expo (ICME), 2019Dropout 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 +5 more
openaire +1 more source
Denoising Convolutional Neural Network
2015 IEEE International Conference on Information and Automation, 2015Convolutional 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 +2 more
openaire +1 more source
Restricted Convolutional Neural Networks
Neural Processing Letters, 2018In this paper, a new type of convolutional neural network is proposed which is inspired by cellular automata research. This model is referred to as “restricted convolutional neural network” and its characteristic is that the feature maps are not fully connected, i.e.
Mehran Mirkhan, Mohammad Reza Meybodi
openaire +1 more source
In vitro convolutional neural networks
Nature Machine Intelligence, 2022Neural networks can be implemented by using purified DNA molecules that interact in a test tube. Convolutional neural networks to classify high-dimensional data have now been realized in vitro, in one of the most complex demonstrations of molecular programming so far. ; © 2022 Springer Nature Limited. Published 11 July 2022.
openaire +2 more sources
A-optimal convolutional neural network
Neural Computing and Applications, 2016In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model.
Zihong Yin +5 more
openaire +1 more source
A Survey on Convolution Neural Networks
2020 IEEE REGION 10 CONFERENCE (TENCON), 2020Major tools to implement any Artificial Intelligence and Machine Learning systems are Symbolic AI and Artificial Neural Network (ANN) AI. ANN has made a dramatic improvement in the versatile area of Machine Learning (ML). ANN is a gathering of vast number of weighted interconnected artificial neurons, initially invented with the inspiration of ...
openaire +1 more source
Sparse Convolutional Neural Networks
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015Deep neural networks have achieved remarkable performance in both image classification and object detection problems, at the cost of a large number of parameters and computational complexity. In this work, we show how to reduce the redundancy in these parameters using a sparse decomposition. Maximum sparsity is obtained by exploiting both inter-channel
Liu, Baoyuan +4 more
openaire +2 more sources
Quadtree Convolutional Neural Networks
2018This paper presents a Quadtree Convolutional Neural Network (QCNN) for efficiently learning from image datasets representing sparse data such as handwriting, pen strokes, freehand sketches, etc. Instead of storing the sparse sketches in regular dense tensors, our method decomposes and represents the image as a linear quadtree that is only refined in ...
Pradeep Kumar Jayaraman +3 more
openaire +1 more source
Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
ACM Computing Surveys, 2022Claudio Filipi Goncalves Dos Santos +1 more
exaly
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
IEEE Transactions on Neural Networks and Learning Systems, 2022Fan Liu, Zewen Li, Shouheng Peng
exaly