39,064 Hits in 4.5 sec

Collaborative Memory Network for Recommendation Systems

Travis Ebesu, Bin Shen, Yi Fang
2018 The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18  
However, existing methods compose deep learning architectures with the latent factor model ignoring a major class of CF models, neighborhood or memory-based approaches.  ...  We propose Collaborative Memory Networks (CMN), a deep architecture to unify the two classes of CF models capitalizing on the strengths of the global structure of latent factor model and local neighborhood-based  ...  Since HR and NDCG show similar patterns, we focus our analysis on NDCG.  ... 
doi:10.1145/3209978.3209991 dblp:conf/sigir/EbesuSF18 fatcat:dixbrvd6o5gd5kqziruxyn2hb4

An explainability framework for cortical surface-based deep learning [article]

Fernanda L. Ribeiro, Steffen Bollmann, Ross Cunnington, Alexander M. Puckett
2022 arXiv   pre-print
surface model.  ...  While most explainability methods have been designed for traditional deep learning, some have been further developed for geometric deep learning, in which data are predominantly represented as graphs.  ...  Region of interest Similar to our previous study [28] , we narrow our analysis to visual areas defined by a surface-based probabilistic atlas [43] .  ... 
arXiv:2203.08312v1 fatcat:dmbnbjr6lnc3nbm4paww3znbzu

Dynamic Deep Multi-modal Fusion for Image Privacy Prediction

Ashwini Tonge, Cornelia Caragea
2019 The World Wide Web Conference on - WWW '19  
The approach considers three stages to predict the privacy of a target image, wherein we first identify the neighborhood images that are visually similar and/or have similar sensitive content as the target  ...  Then, we estimate the competence of the modalities based on the neighborhood images.  ...  ACKNOWLEDGMENTS is research is supported by the NSF grant #1421970. e computing for this project was performed on Amazon Web Services.  ... 
doi:10.1145/3308558.3313691 dblp:conf/www/TongeC19 fatcat:5g3dhzc5wfghjounz4pgtktivq

A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm [article]

Sungwon Han, Yizhan Xu, Sungwon Park, Meeyoung Cha, Cheng-Te Li
2020 arXiv   pre-print
This paper proposes a new unsupervised embedding approach, called Super-AND, which extends the current state-of-the-art model.  ...  Super-AND has its unique set of losses that can gather similar samples nearby within a low-density space while keeping invariant features intact against data augmentation.  ...  Top-1 classification accuracy was used for evaluation. Results & Component analysis Baseline models.  ... 
arXiv:2002.12158v1 fatcat:jvdkn36nyvhxrczibke7ioyn3m

Learning Convolutional Nonlinear Features for K Nearest Neighbor Image Classification

Weiqiang Ren, Yinan Yu, Junge Zhang, Kaiqi Huang
2014 2014 22nd International Conference on Pattern Recognition  
However, for vision tasks other than end-to-end classification, such as K Nearest Neighbor classification, the learned intermediate features are not necessary optimal for the specific problem.  ...  In this paper, we aim to exploit the power of deep convolutional networks and optimize the output feature layer with respect to the task of K Nearest Neighbor (kNN) classification.  ...  (LMNN) [21] and Neighborhood Components Analysis (NCA) [14] .  ... 
doi:10.1109/icpr.2014.746 dblp:conf/icpr/RenYZH14 fatcat:7ozsr5o6jjeype4xq2gmo3btoq

Deep Convolutional Self-organizing Map Network for Robust Handwritten Digit Recognition

Saleh Aly, Sultan Almotairi
2020 IEEE Access  
The 2D SOM grid is commonly used for either data visualization or feature extraction. However, this work employs high dimensional map size to create a new deep network.  ...  Experimental results reveal that the performance of DCSOM outperforms state-of-the-art methods for noisy digits and achieve a comparable performance with other complex deep learning architecture for other  ...  ACKNOWLEDGMENT The authors extend their appreciation to the Deanship of Scientific Research at Majmaah University for funding this work.  ... 
doi:10.1109/access.2020.3000829 fatcat:joljst3o5vdefp6lww6x37afwm

Visualization Framework for High-Dimensional Spatio-Temporal Hydrological Gridded Datasets Using Machine-Learning Techniques

Abeer Mazher
2020 Water  
Machine learning (ML) based DRTs for data visualization i.e., principal component analysis (PCA), generative topographic mapping (GTM), t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold  ...  The workflow is applied to an output of an Australian Water Resource Assessment (AWRA) model for Tasmania, Australia.  ...  Acknowledgments: I would like to thank Luk Peeters (CSIRO, Deep Earth Imaging-Future Science Platform) contribution in concept designing and refining the manuscript.  ... 
doi:10.3390/w12020590 fatcat:ye5mlwu4ynhnpgrbjoi5nzzj5a

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Ke Sun, Lei Wang, Bo Xu, Wenhong Zhao, Shyh Wei Teng, Feng Xia
2020 IEEE Access  
Similar to SDNE framework, the deep model used by TransNet for learning edge representation is deep autoencoder, and the reconstruction loss function is a distance-based model similar to LE [45] , LLE  ...  PATCHY-SAN model contains four steps: (1) node sequence selection; (2) neighborhood graph construction; (3) normalizing the extracting neighborhood graph; (4) combining with existing CNN components, which  ... 
doi:10.1109/access.2020.3037118 fatcat:kca6htfarjdjpmtwcvbsppfzui

Tumor tissue classification based on micro-hyperspectral technology and deep learning

Bingliang Hu, Jian Du, Zhoufeng Zhang, Quan Wang
2019 Biomedical Optics Express  
The combination of deep learning model and micro-spectral analysis provides new ideas for the research of medical pathology.  ...  Based on the difference in spectral-spatial features between gastric cancer tissue and normal tissue in the wavelength of 410-910 nm, we propose a deep-learning model-based analysis method for gastric  ...  Funding Xi'an Key Laboratory for Biomedical Spectroscopy (201805050ZD1CG34); National Natural Science Foundation of China (61501456).  ... 
doi:10.1364/boe.10.006370 pmid:31853405 pmcid:PMC6913401 fatcat:ephqnkiqezaynhkljk5m2wzc7e

Visualization and Analysis Model of Industrial Economy Status and Development Based on Knowledge Graph and Deep Neural Network

Jing Quan, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
a visual analysis model of economic development based on knowledge mapping combined with a deep neural network algorithm.  ...  This paper provides a visual analysis method to sort and classify multivariate data.  ...  Figure 1 : 1 Figure 1: Overall architecture of the two-tower recall model for knowledge graphs. Figure 3 :Figure 2 : 32 Figure 3: Visualization analysis model architecture.  ... 
doi:10.1155/2022/7008093 pmid:35528336 pmcid:PMC9071965 fatcat:h6d3ty5rcbb3jp4na5tsopi34e

Improving Generalization via Scalable Neighborhood Component Analysis [article]

Zhirong Wu, Alexei A. Efros, Stella X. Yu
2018 arXiv   pre-print
We use a deep neural network to learn the visual feature that preserves the neighborhood structure in the semantic space, based on the Neighborhood Component Analysis (NCA) criterion.  ...  Limited by its computational bottlenecks, we devise a mechanism to use augmented memory to scale NCA for large datasets and very deep networks.  ...  ZW would like to thank Yuanjun Xiong for helpful discussions.  ... 
arXiv:1808.04699v1 fatcat:auyj2rlrzfedli4f4w7aubf5zu

DGCyTOF: Deep learning with graphic cluster visualization to predict cell types of single cell mass cytometry data

Lijun Cheng, Pratik Karkhanis, Birkan Gokbag, Yueze Liu, Lang Li, Kathryn Miller-Jensen
2022 PLoS Computational Biology  
Analysis (PCA), Factor Analysis (FA), Independent Component Analysis (ICA), Isometric Feature Mapping (Isomap), t-distributed Stochastic Neighbor Embedding (t-SNE), and Uniform Manifold Approximation  ...  A deep learning with graphic cluster (DGCyTOF) visualization is developed as a new integrated embedding visualization approach in identifying canonical and new cell types.  ...  Such dimension-reduction techniques include Principal Component Analysis (PCA) [28] , Factor Analysis (FA) [29] , Independent Component Analysis (ICA) [30] , Isometric Feature Mapping (Isomap) [31]  ... 
doi:10.1371/journal.pcbi.1008885 pmid:35404970 pmcid:PMC9060369 fatcat:ly7rxohhwnhn7hrbzholxsufgm

Visual Perception of Building and Household Vulnerability from Streets [article]

Chaofeng Wang, Sarah Elizabeth Antos, Jessica Grayson Gosling Goldsmith, Luis Miguel Triveno
2022 arXiv   pre-print
made by our model could be used to approximate vulnerability conditions with a lower budget and in selected areas.  ...  We then check its potential for scalability and higher level reliability.  ...  This work seems to be the first study to use deep learning-based image analysis for household vulnerability study.  ... 
arXiv:2205.14460v1 fatcat:lfp5wv34mvasdnhwxrigavoi7i

Structural Deep Network Embedding

Daixin Wang, Peng Cui, Wenwu Zhu
2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16  
By jointly optimizing them in the semi-supervised deep model, our method can preserve both the local and global network structure and is robust to sparse networks.  ...  More specifically, we first propose a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non-linear network structure.  ...  and Discussions In this section, we present some analysis and discussions of the proposed semi-supervised deep model of SDNE.  ... 
doi:10.1145/2939672.2939753 dblp:conf/kdd/WangC016 fatcat:4kk2zlbl55h4vmecoad6qfr5jm

A Unified Model for Recommendation with Selective Neighborhood Modeling [article]

Jingwei Ma and Jiahui Wen and Panpan Zhang and Guangda Zhang and Xue Li
2020 arXiv   pre-print
These two components are combined into a unified model to complement each other for the recommendation task.  ...  those similar neighbors to comprise neighborhood representations.  ...  [45] use pre-trained CNNs model to exploit visual content from images, and integrate those visual features for recommending point of interest.  ... 
arXiv:2010.08547v1 fatcat:ajekzn5ec5bcvatgz3nlk6p4um
« Previous Showing results 1 — 15 out of 39,064 results