6,121 Hits in 4.4 sec

A Gentle Introduction to Deep Learning for Graphs [article]

Davide Bacciu, Federico Errica, Alessio Micheli, Marco Podda
2019 arXiv   pre-print
This work is designed as a tutorial introduction to the field of deep learning for graphs.  ...  The adaptive processing of graph data is a long-standing research topic which has been lately consolidated as a theme of major interest in the deep learning community.  ...  This paper takes pace from this historical perspective to provide a gentle introduction to the field of neural networks for graphs, also referred to as deep learning for graphs in modern terminology.  ... 
arXiv:1912.12693v1 fatcat:lww6akhmuvbe5hu335hl7ggghu

Deep Adversarial Learning for

William Yang Wang, Sameer Singh, Jiwei Li
2019 Proceedings of the 2019 Conference of the North  
In this tutorial, we provide a gentle introduction to the foundation of deep adversarial learning, as well as some practical problem formulations and solutions in NLP.  ...  We describe recent advances in deep adversarial learning for NLP, with a special focus on generation, adversarial examples & rules, and dialogue.  ...  In particular, we start with the gentle introduction to the fundamentals of adversarial learning.  ... 
doi:10.18653/v1/n19-5001 dblp:conf/naacl/WangSL19 fatcat:d4epvsksbnhmbakslrbqr5exhu

Deep Reinforcement Learning for NLP

William Yang Wang, Jiwei Li, Xiaodong He
2018 Proceedings of ACL 2018, Tutorial Abstracts  
In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP.  ...  We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction.  ...  In particular, we start with the gentle introduction to the fundamentals of reinforcement learning (Sutton and Barto, 1998; Sutton et al., 2000) .  ... 
doi:10.18653/v1/p18-5007 dblp:conf/acl/WangLH18 fatcat:otigakcyzrgwlhcwbigvdp7qgm

DFM-GCN: A Multi-Task Learning Recommendation Based on a Deep Graph Neural Network

Yan Xiao, Congdong Li, Vincenzo Liu
2022 Mathematics  
Among the inherent problems in recommendation systems are data sparseness and cold starts; the solutions to which lie in the introduction of knowledge graphs to improve the performance of the recommendation  ...  Therefore, a DeepFM Graph Convolutional Network (DFM-GCN) model was proposed to alleviate the above issues.  ...  The learning curves for the Top 10 were more gentle than the Top 100 in the early steps, which showed that the model mainly focused on recalling more reliable candidate items.  ... 
doi:10.3390/math10050721 fatcat:z3jylmbkgzfrziwf3zc5fcluci

Latent Structure Models for Natural Language Processing

André F. T. Martins, Tsvetomila Mihaylova, Nikita Nangia, Vlad Niculae
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts  
It will offer a gentle introduction to recent advances in structured modeling with discrete latent variables, which were not previously covered in any ACL/EMNLP/IJCNLP/NAACL related tutorial.  ...  . • machine learning: familiarity with neural networks for NLP, basic understanding of backpropagation and computation graphs.  ... 
doi:10.18653/v1/p19-4001 dblp:conf/acl/MartinsMNN19 fatcat:5vdzt5p23ncqrcngougdsddcx4

A Gentle Introduction to Graph Neural Networks

Benjamin Sanchez-Lengeling, Emily Reif, Adam Pearce, Alex Wiltschko
2021 Distill  
For attribution in academic contexts, please cite this work as Sanchez-Lengeling, et al., "A Gentle Introduction to Graph Neural Networks", Distill, 2021.  ...  BibTeX citation @article{sanchez-lengeling2021a, author = {Sanchez-Lengeling, Benjamin and Reif, Emily and Pearce, Adam and Wiltschko, Alex}, title = {A Gentle Introduction to Graph Neural Networks  ... 
doi:10.23915/distill.00033 fatcat:7sa54cvytzecnm3ctjxa4mj3ta

Transfer learning-based Plant Disease Detection

2021 International journal for innovative engineering and management research  
Deep Neural Networks in the field of Machine Learning (ML) are broadly used for deep learning.  ...  This study provides a transfer learning-based solution for detecting multiple diseases in several plant varieties using simple leaf images of healthy and diseased plants taken from PlantVillage dataset  ...  Introduction Today, modern technology allows us to grow crops in quantities necessary for a gentle food supply for billions of individuals.  ... 
doi:10.48047/ijiemr/v10/i03/99 fatcat:7gwa3st6szdqtbcl5kp26vqbje

Structural Deep Clustering Network [article]

Deyu Bo, Xiao Wang, Chuan Shi, Meiqi Zhu, Emiao Lu, Peng Cui
2020 arXiv   pre-print
for clustering is a crucial requirement.  ...  Specifically, we design a delivery operator to transfer the representations learned by autoencoder to the corresponding GCN layer, and a dual self-supervised mechanism to unify these two different deep  ...  Hence learning an effective data representation is a crucial prerequisite for deep clustering.  ... 
arXiv:2002.01633v2 fatcat:c2l57f6rszf5pfrdwcncaabbnm

Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition

Yansong Tang, Yi Tian, Jiwen Lu, Peiyang Li, Jie Zhou
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper, we propose a deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous  ...  Since the choices of selecting representative frames are multitudinous for each video, we model the frame selection as a progressive process through deep reinforcement learning, during which we progressively  ...  Moreover, we employ a graph-based deep learning model to capture both the intrinsic and extrinsic dependencies between human joints.  ... 
doi:10.1109/cvpr.2018.00558 dblp:conf/cvpr/TangTLL018 fatcat:gv6x3vml7fe3peiabn5qxa763y

Near Maximum Likelihood Decoding with Deep Learning [article]

Eliya Nachmani, Yaron Bachar, Elad Marciano, David Burshtein, Yair Be'ery
2018 arXiv   pre-print
Simulations of the hessian and the condition number show why the learning process is accelerated. We demonstrate the decoding algorithm for various linear block codes of length up to 63 bits.  ...  A novel and efficient neural decoder algorithm is proposed. The proposed decoder is based on the neural Belief Propagation algorithm and the Automorphism Group.  ...  INTRODUCTION In the last few years Deep Learning methods were applied to communication systems, for example in [1]- [8] .  ... 
arXiv:1801.02726v1 fatcat:gmdncv26e5gorfpta76awjfv5y

Deep Learning and Open Set Malware Classification: A Survey [article]

Jingyun Jia
2020 arXiv   pre-print
This survey provides an overview of different deep learning techniques, a discussion of OSR and graph representation solutions and an introduction of malware classification systems.  ...  The dramatic increase of malware has led to a research area of not only using cutting edge machine learning techniques classify malware into their known families, moreover, recognize the unknown ones,  ...  CONCLUSIONS We provide a brief introduction of several deep neural network structures, and an overview of existing OSR, a discussion on learning graph representation and malware classification in this  ... 
arXiv:2004.04272v1 fatcat:332sfs7davh2hkxoehiyjta2y4

A Gentle Introduction to Deep Learning in Medical Image Processing [article]

Andreas Maier, Christopher Syben, Tobias Lasser, Christian Riess
2018 arXiv   pre-print
This paper tries to give a gentle introduction to deep learning in medical image processing, proceeding from theoretical foundations to applications.  ...  Doing so allows us to understand the reasons for the rise of deep learning in many application domains.  ...  Acknowledgements We express our thanks to Katharina Breininger, Tobias Würfl, and Vincent Christlein, who did a tremendous job when we created the deep learning course at the University of Erlangen-Nuremberg  ... 
arXiv:1810.05401v2 fatcat:dtd5eyj65jbfdjtsywxw3ilaqq

DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network

Jinming Zhang, Xiangyun Hu, Hengming Dai, ShenRun Qu
2020 Remote Sensing  
However, most of the existing deep learning frameworks, such as PointNet, dynamic graph convolutional neural network (DGCNN), and SparseConvNet, cannot consider the particularity of ALS point clouds.  ...  Machine learning, especially deep learning methods, has shown powerful feature extraction in accomplishing point cloud classification.  ...  Acknowledgments: The authors thank Guangzhou Jiantong Surveying, Mapping, and Geographic Information Technology Ltd. for providing the data used in this research project.  ... 
doi:10.3390/rs12010178 fatcat:py7wp4767fejdphfkye7rmp4xe

A modified technique for recognizing facial expression

Bhawesh Rajpal, Nitin Prasad, Kaushal Kishore Rao Mangalore, Nikhitha Pradeep, Ravi Shastri
2020 Journal of Applied Research on Industrial Engineering  
This facial region is passed on to the model trained by a CNN where facial features are matched with the features specified in the model.  ...  In the initial processing stage the facial region is identified using a Haar cascade classifier.  ...  An & Liu [49] 2019 The authors use deep learning to recognize facial expressions, they proposed a new function to initialize CNN and LSTM networks. Kimet al.  ... 
doi:10.22105/jarie.2020.259293.1216 doaj:79760e41d6564578ad18953c40756591 fatcat:wuwtd6x5qbhd3fdbfwvqrskpqu

DEM Void Filling Based on Context Attention Generation Model

Chunsen Zhang, Shu Shi, Yingwei Ge, Hengheng Liu, Weihong Cui
2020 ISPRS International Journal of Geo-Information  
Based on the algorithm of deep learning, this paper aims to train a deep generation model (DGM) to complete the DEM void filling task.  ...  A certain amount of DEM data and a randomly generated mask are taken as network inputs, along which the reconstruction loss and generative adversarial network (GAN) loss are used to assist network training  ...  The introduction of a discriminate model leads to the emergence of a game type training process.  ... 
doi:10.3390/ijgi9120734 fatcat:lovvtxo3kjgufaagk5gemy4v3i
« Previous Showing results 1 — 15 out of 6,121 results