Results 11 to 20 of about 204,781 (309)
Canonical convolutional neural networks [PDF]
2022 International Joint Conference on Neural Networks (IJCNN), 2022 We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode ...
Lokesh Veeramacheneni +3 more
openaire +3 more sources
Powerset Convolutional Neural Networks [PDF]
CoRR, 2019 We present a novel class of convolutional neural networks (CNNs) for set functions, i.e., data indexed with the powerset of a finite set. The convolutions are derived as linear, shift-equivariant functions for various notions of shifts on set functions.
Wendler, Chris +2 more
core +7 more sources
Convolutional Neural Networks With Dynamic Regularization [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2021 Regularization is commonly used for alleviating overfitting in machine learning. For convolutional neural networks (CNNs), regularization methods, such as DropBlock and Shake-Shake, have illustrated the improvement in the generalization performance. However, these methods lack a self-adaptive ability throughout training.
Yi Wang 0068 +3 more
openaire +6 more sources
An Attention Module for Convolutional Neural Networks [PDF]
, 2021 Attention mechanism has been regarded as an advanced technique to capture long-range feature interactions and to boost the representation capability for convolutional neural networks.
Zhu, B. (author) +3 more
core +1 more source
Convolutional neural networks for medical image processing applications [PDF]
, 2022 The rise in living standards increases the expectation of people in almost every field. At the forefront is health. Over the past few centuries, there have been major developments in healthcare.
Öztürk Ş.
core +1 more source
Convolution-Bidirectional Temporal Convolutional Network for Protein Secondary Structure Prediction
IEEE Access, 2022 As a basic feature extraction method, convolutional neural networks have some information loss problems when dealing with sequence problems, and a temporal convolutional network can compensate for this problem.
Yunqing Zhang, Yuming Ma, Yihui Liu
doaj +1 more source
Measurement: Sensors, 2021 The convolutional neural network is a subfield of artificial neural networks and has made great achievements in various domains over the past decade.
Hengyi Li +5 more
doaj +1 more source
STUDY OF HARDWARE-IMPLEMENTED CONVOLUTIONAL NEURAL NETWORKS OF THE U-NET CLASS
Известия Томского политехнического университета: Промышленная кибернетика, 2023 The authors have developed and implemented two convolutional neural networks of the U-Net class: a modification of the classical U-Net and a UNet with dilated convolutions. For training and testing convolutional neural networks, data sets were used based
Ivan V. Zoev +3 more
doaj +1 more source
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects [PDF]
, 2021 A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much
Zhou, Jun +4 more
core +1 more source
Orthogonal Convolutional Neural Networks [PDF]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonality on convolutional filters. We develop an efficient approach to impose filter orthogonality on a convolutional layer based on the doubly block-Toeplitz matrix ...
Jiayun Wang +3 more
openaire +2 more sources