25 Hits in 1.7 sec

MagNet: A Neural Network for Directed Graphs [article]

Xitong Zhang and Yixuan He and Nathan Brugnone and Michael Perlmutter and Matthew Hirn
2021 arXiv   pre-print
The prevalence of graph-based data has spurred the rapid development of graph neural networks (GNNs) and related machine learning algorithms.  ...  Yet, despite the many datasets naturally modeled as directed graphs, including citation, website, and traffic networks, the vast majority of this research focuses on undirected graphs.  ...  , the model includes graph convolutional layers without the high-order approximation and inception module.  ... 
arXiv:2102.11391v2 fatcat:y4wpcfcvivdrdhxkjfhnf5kwny

Developing plastic recycling classifier by deep learning and directed acyclic graph residual network

Ahmed Burhan Mohammed, Ahmad Abdullah Mohammed Al-Mafrji, Moumena Salah Yassen, Ahmad H. Sabry
2022 Eastern-European Journal of Enterprise Technologies  
To optimize the gradient flow and enable deeper training for network design with multi label classifier, this study suggests a residual-based deep learning convolutional neural network.  ...  The DAG network's residual-based architecture features shortcut connections that bypass some levels of the network, allowing gradients of network parameters to travel freely among the network output layers  ...  Several types of graph: a -simple graph; b -simple digraph; c -digraph with a highlighted cycle; d -simple dag Fig. 3 .Fig. 4 . 34 Fig. 3.  ... 
doi:10.15587/1729-4061.2022.254285 fatcat:amyq3v2ndjb2fjekys64i65lky

DIGRAC: Digraph Clustering Based on Flow Imbalance [article]

Yixuan He and Gesine Reinert and Mihai Cucuringu
2022 arXiv   pre-print
We introduce a graph neural network framework to obtain node embeddings for directed networks in a self-supervised manner, including a novel probabilistic imbalance loss, which can be used for network  ...  Node clustering is a powerful tool in the analysis of networks.  ...  Digraph inception convolutional networks. Advances in Neural Information Processing Systems, 33, 2020. [43] Zekun Tong, Yuxuan Liang, Changsheng Sun, David S Rosenblum, and Andrew Lim.  ... 
arXiv:2106.05194v6 fatcat:udznmb7lzjbe3i5thmpi27ek6e

Cribriform pattern detection in prostate histopathological images using deep learning models [article]

Malay Singh, Emarene Mationg Kalaw, Wang Jie, Mundher Al-Shabi, Chin Fong Wong, Danilo Medina Giron, Kian-Tai Chong, Maxine Tan, Zeng Zeng, Hwee Kuan Lee
2019 arXiv   pre-print
We propose using deep neural networks for cribriform pattern classification in prostate histopathological images. 163708 Hematoxylin and Eosin (H&E) stained images were extracted from histopathologic tissue  ...  [20] proposed an algorithm based on deep convolutional networks that classify WSI of breast biopsies into five diagnostic categories. Araujo et al.  ...  [21] designed a multi-scale deep convolutional neural network to classify normal tissue, benign lesion, in situ carcinoma, and invasive carcinoma, and in two classes, carcinoma and non-carcinoma.  ... 
arXiv:1910.04030v1 fatcat:4uzdt7lmlzfnbjh6pjptwpua4m

2020 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 31

2020 IEEE Transactions on Neural Networks and Learning Systems  
Zhe, X., +, TNNLS May 2020 1681-1695 Deep Inception-Residual Laplacian Pyramid Networks for Accurate Single-Image Super-Resolution.  ...  Yi, S., +, TNNLS June 2020 2153-2163 Deep Inception-Residual Laplacian Pyramid Networks for Accurate Single-Image Super-Resolution.  ...  ., +, TNNLS Oct. 2020 3777-3787 On the Working Principle of the Hopfield Neural Networks and its Equivalence to the GADIA in Optimization. Uykan, Z.,  ... 
doi:10.1109/tnnls.2020.3045307 fatcat:34qoykdtarewhdscxqj5jvovqy

Asymmetric Graph Representation Learning [article]

Zhuo Tan, Bin Liu, Guosheng Yin
2021 arXiv   pre-print
Despite the enormous success of graph neural networks (GNNs), most existing GNNs can only be applicable to undirected graphs where relationships among connected nodes are two-way symmetric (i.e., information  ...  [28] further exploit the kth-order proximity between two nodes in a digraph by the inception network [26] , which not only allows the model to learn features of different sizes within one convolutional  ...  GCN In the graph convolutional networks (GCN) [13] , initially motivated by spectral graph convolutions [4, 6] , the AGGREGATE and COMBINE steps are integrated as follows, h l v = ReLU W • MEAN h l−1  ... 
arXiv:2110.07436v1 fatcat:yflvry72yzholb7rxbf26cjemu


Shyam Sankar
2020 International Research Journal of Computer Science  
A hybrid network combining Deep Convolutional Neural Networks (DCNN) and Deep Recurrent Neural Network (DRNN) was used for robust inertial gait feature representation. B.  ...  The proposed method uses an encoder-decoder network to learn domain specific features. This is followed by stacking inception layers used to generate palm vein feature sets.  ... 
doi:10.26562/irjcs.2020.v0709.004 fatcat:be2f2rofonhvbjft7zwgid3q6a

Methods for Measuring Geodiversity in Large Overhead Imagery Datasets

Aaron M. Wesley, Timothy C. Matisziw
2021 IEEE Access  
neural networks (CNNs) [14] .  ...  The Inception v3 network pretrained on the 1000-class ImageNet dataset [90] is again used to calculate r GeoIS  for each subregion grid of the random and control feature sets.  ... 
doi:10.1109/access.2021.3096034 fatcat:keclmo4zaff3lbfiote2tldqc4

Graph Neural Networks for Natural Language Processing: A Survey [article]

Lingfei Wu, Yu Chen, Kai Shen, Xiaojie Guo, Hanning Gao, Shucheng Li, Jian Pei, Bo Long
2021 arXiv   pre-print
In this survey, we present a comprehensive overview onGraph Neural Networks(GNNs) for Natural Language Processing.  ...  Reinceptione: Relation-aware inception network with joint local-global structural information for knowledge graph embedding.  ...  A neural multi-digraph model for Chinese NER with gazetteers.  ... 
arXiv:2106.06090v1 fatcat:zvkhinpcvzbmje4kjpwjs355qu

CSITSS Proceedings 2020

2019 2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)  
Available: Image processing; Image Analysis; Image Classification; Convolutional Neural Network; CNN; ILSVRC; ZFNet; Inception V1; Inception V2; Inception V3;  ...  Convolutional Neural Networks Convolutional Neural Network (CNN) is a deep learning model which is generally used for image recognition or classification.  ...  Product-based Neural Networks In this paper we have focused on the general architecture of ontology-based Information Retrieval used for Kannada.  ... 
doi:10.1109/csitss47250.2019.9031039 fatcat:yehi3bfgbva7xm74vp3a3i54pu

A Critical and Moving-Forward View on Quantum Image Processing [article]

Fei Yan, Salvador E. Venegas-Andraca, Kaoru Hirota
2020 arXiv   pre-print
PageRank is an algorithm developed to provide a quantitative approach to the qualitative notion of node importance in a digraph.  ...  . • From its inception, QIMP has benefited from the talent and efforts of a research community vastly composed of computer scientists, mathematicians and computer engineers.  ... 
arXiv:2006.08747v1 fatcat:5bzbxl3usrguxoi3es3natvdgm

Back to the biology in systems biology: What can we learn from biomolecular networks?

S. Huang
2004 Briefings in Functional Genomics & Proteomics  
What do networks tell us?  ...  To study the function of genes, it is necessary not only to see them in the context of gene networks, but also to reach beyond describing network topology and to embrace the global dynamics of networks  ...  Maliackal for helpful discussions on networks and Donald E. Ingber for his continuous support.  ... 
doi:10.1093/bfgp/2.4.279 pmid:15163364 fatcat:pcr376nwmva5fiohwyiwvcmmn4

Recent Advances in Formations of Multiple Robots

Saar Cohen, Noa Agmon
2021 Current Robotics Reports  
Inspired by convolutional neural networks (CNNs), they make use of a new architecture called graph convolutional networks (GCNs), which utilize a bank of graph filters.  ...  The DNN is composed of a three-layered convolutional neural network (CNN) and a fully connected (FC) network to approximate the control policy function.  ... 
doi:10.1007/s43154-021-00049-2 fatcat:xu4xzhaqpvduljk6pvf34z6fva

Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications [article]

Giorgio Roffo
2017 arXiv   pre-print
cortex and the layers in a convolutional neural network.  ...  The ranking model is solved with a deep convolutional neural network (CNN).  ... 
arXiv:1706.05933v1 fatcat:oc4xtmyqkvf4njpqsojewv75qu

Autonomous perception and decision-making in cyber-physical systems

Asok Ray
2013 2013 8th International Conference on Computer Science & Education  
In such a scenario of networked physical systems, the distribution of physical entities determines the underlying network topology and the interaction among the entities forms the abstract cyber space.  ...  Thus the study of MAS has been immensely interdisciplinary in nature from its inception.  ...  The digraph representation is illustrated in Figure 4.1.The relational probabilistic finite state automata (PFSA) are discovered using Figure 4 . 1 . 41 Composite Pattern Digraph xD-Markov machine construction  ... 
doi:10.1109/iccse.2013.6554173 fatcat:243gtheg6vd6jaz7pauyr447aa
« Previous Showing results 1 — 15 out of 25 results