693 Hits in 7.0 sec

Neural network layers as parametric spans [article]

Mattia G. Bergomi, Pietro Vertechi
2022 arXiv   pre-print
Properties such as composability and automatic differentiation made artificial neural networks a pervasive tool in applications.  ...  Tackling more challenging problems caused neural networks to progressively become more complex and thus difficult to define from a mathematical perspective.  ...  Integration theories Our goal is to represent the structure of a linear layer of a neural network-a bilinear map from the input and parameters to the output-via a collection of maps in a familiar category  ... 
arXiv:2208.00809v2 fatcat:kn2orttjnbhoxp63virgzbuiay

Integrative Analysis of Patient Health Records and Neuroimages via Memory-based Graph Convolutional Network [article]

Xi Sheryl Zhang, Jingyuan Chou, Fei Wang
2019 arXiv   pre-print
In this paper, we proposed a framework, Memory-Based Graph Convolution Network (MemGCN), to perform integrative analysis with such multi-modal data.  ...  With the arrival of the big data era, more and more data are becoming readily available in various real-world applications and those data are usually highly heterogeneous.  ...  ACKNOWLEDGEMENT Discovery, Pfizer, Piramal, Roche, Sanofi, Servier, TEVA, UCB and Golub Capital.  ... 
arXiv:1809.06018v4 fatcat:tqawiaohcfcrfo4kazsx2fhm5y

Estimating latent positions of actors using Neural Networks in R with GCN4R [article]

Joshua Levy, Carly A Bobak, Brock Christensen, Louis J Vaickus, A. James O'Malley
2020 bioRxiv   pre-print
Here, we introduce GCN4R, an R library for fitting graph neural networks on independent networks to aggregate actor covariate information to yield meaningful embeddings for a variety of network-based tasks  ...  Network analysis methods are useful to better understand and contextualize relationships between entities.  ...  of components), while convolutional neural networks (CNN) slide learnable filters across images (matrix or multidimensional array; 2-3 rank tensor) to extract and integrate lower order structural and  ... 
doi:10.1101/2020.11.02.364935 fatcat:qkiyeymuxjalbhx6blekhzpg3a

2021 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 32

2021 IEEE Transactions on Neural Networks and Learning Systems  
The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  The Subject Index contains entries describing the item under all appropriate subject headings, plus the first author's name, the publication abbreviation, month, and year, and inclusive pages.  ...  Visually Connected Graph Convolutional Networks.  ... 
doi:10.1109/tnnls.2021.3134132 fatcat:2e7comcq2fhrziselptjubwjme

HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion [article]

Zixuan Huang, Junming Fan, Shenggan Cheng, Shuai Yi, Xiaogang Wang, Hongsheng Li
2020 arXiv   pre-print
inputs and sparse feature maps is also proposed.  ...  To effectively utilize multi-scale features, we propose three novel sparsity-invariant operations, based on which, a sparsity-invariant multi-scale encoder-decoder network (HMS-Net) for handling sparse  ...  An energy function is designed and solved to solve the depth upsampling problem. Hui et al. [31] proposed a convolution neural network, which fused the RGB guidance signals at different stages.  ... 
arXiv:1808.08685v2 fatcat:pckzqe5oszcvtenafktze7prvi

Deep Recurrent Level Set for Segmenting Brain Tumors [chapter]

T. Hoang Ngan Le, Raajitha Gummadi, Marios Savvides
2018 Lecture Notes in Computer Science  
The proposed DRLS consists of three layers, i.e, Convolutional layers, Deconvolutional layers with skip connections and LevelSet layers.  ...  Convolutional layer learns visual representation of brain tumor at different scales.  ...  surrounding edema are often diffused, poorly contrasted, and have extended tentacle-like structures.  ... 
doi:10.1007/978-3-030-00931-1_74 fatcat:iegmnkwqprcrpjbvxtckc2klfa

Structural inference embedded adversarial networks for scene parsing

ZeYu Wang, YanXia Wu, ShuHui Bu, PengCheng Han, GuoYin Zhang, Quanquan Gu
2018 PLoS ONE  
The generator of our SIEANs, a novel designed scene parsing network, makes full use of convolutional neural networks and long short-term memory networks to learn the global contextual information of objects  ...  To take both advantages of the structural learning and adversarial training simultaneously, we propose a novel deep learning network architecture called Structural Inference Embedded Adversarial Networks  ...  Acknowledgments Our work is supported by the National Key Research and Development Program (2016YFB1000400), the Central University Free Exploration Fund (HEUCF170605), the Harbin Outstanding Young Talents  ... 
doi:10.1371/journal.pone.0195114 pmid:29649294 pmcid:PMC5896926 fatcat:c7vamyx6jre4zjw3pjq2aa3c2u

Studying deep convolutional neural networks with hexagonal lattices for imaging atmospheric Cherenkov telescope event reconstruction [article]

D. Nieto, A. Brill, Q. Feng, M. Jacquemont, B. Kim, T. Miener, T. Vuillaume
2019 arXiv   pre-print
Deep convolutional neural networks (DCNs) are a promising machine learning technique to reconstruct events recorded by imaging atmospheric Cherenkov telescopes (IACTs), but require optimization to reach  ...  Strategies directed to tackle this challenge range from the conversion of the hexagonal lattices onto square lattices by means of oversampling or interpolation to the implementation of hexagonal convolutional  ...  This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreements 653477 and 824064.  ... 
arXiv:1912.09898v1 fatcat:2ijrztpc2jf7nojwdz6gijpja4

Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network [article]

Huaiqian You, Yue Yu, Marta D'Elia, Tian Gao, Stewart Silling
2022 arXiv   pre-print
Neural operators have recently become popular tools for designing solution maps between function spaces in the form of neural networks.  ...  Our NKN stems from the interpretation of the neural network as a discrete nonlocal diffusion reaction equation that, in the limit of infinite layers, is equivalent to a parabolic nonlocal equation, whose  ...  Yunzhe Tao and Dr. Zongyi Li for sharing their codes and for the helpful discussions.  ... 
arXiv:2201.02217v1 fatcat:obqh3gjhxfc7xcqeqisc3e5nue

Application of machine learning methods to detect and classify Core images using GAN and texture recognition [article]

Daniyar Nurseitov, Kairat Bostanbekov, Galymzhan Abdimanap, Abdelrahman Abdallah, Anel Alimova, Darkhan Kurmangaliyev
2022 arXiv   pre-print
The second problem is filling the hole in the core image by applying the Generative adversarial network(GAN) technique and using Contextual Residual Aggregation(CRA) which creates high frequency residual  ...  The first problem is detecting the cores and segmenting the holes in images by using Faster RCNN and Mask RCNN models respectively.  ...  To determine lithology, a Convolutional Neural Network (CNN) with two convolutional layers, two pooling layers, and one fully-connected layer is used in this work.  ... 
arXiv:2204.14224v1 fatcat:xxfbpsrmlrenpkutnm6yhmvvj4

Deep Radiance Caching: Convolutional Autoencoders Deeper in Ray Tracing [article]

Giulio Jiang, Bernhard Kainz
2020 arXiv   pre-print
Recent research uses Deep Neural Networks to predict indirect lighting on image level, but such methods are commonly limited to diffuse materials and require training on each scene.We present Deep Radiance  ...  DRC employs a denoising neural network with Radiance Caching to support a wide range of material types, without the requirement of offline pre-computation or training for each scene.This offers high performance  ...  Acknowledgements: This work has been kindly supported by Intel R and Nvidia.  ... 
arXiv:1910.02480v2 fatcat:tmikya7qdvarvbps736z3usnw4

Cystoid macular edema segmentation of Optical Coherence Tomography images using fully convolutional neural networks and fully connected CRFs [article]

Fangliang Bai, Manuel J. Marques, Stuart J. Gibson
2017 arXiv   pre-print
In this paper we present a new method for cystoid macular edema (CME) segmentation in retinal Optical Coherence Tomography (OCT) images, using a fully convolutional neural network (FCN) and a fully connected  ...  Our approach is versatile and we believe it can be easily adapted to detect other macular defects.  ...  and hardware deployment from Nicholas French (SPS, Kent).  ... 
arXiv:1709.05324v1 fatcat:5qpn65gvdvclha2dtith7q6bii

Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances [article]

Brian Moser, Federico Raue, Stanislav Frolov, Jörn Hees, Sebastian Palacio, Andreas Dengel
2022 arXiv   pre-print
We complement previous surveys by incorporating the latest developments in the field such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the  ...  ., allowing flexible upsampling, more effective loss functions, and better evaluation metrics.  ...  ACKNOWLEDGMENTS This work was supported by the BMBF projects Ex-plAINN, EDeL, and XAINES (Grant 01IS19074, 01IS19075, and 01IW20005).  ... 
arXiv:2209.13131v1 fatcat:wpzorbxv2zef7k3ekzk6jxaghy

Embedding Physics to Learn Spatiotemporal Dynamics from Sparse Data [article]

Chengping Rao, Hao Sun, Yang Liu
2021 arXiv   pre-print
The coercive embedding mechanism of physics, fundamentally different from physics-informed neural networks based on loss penalty, ensures the network to rigorously obey given physics.  ...  However, the explicit formulation of PDEs for many underexplored processes, such as climate systems, biochemical reaction and epidemiology, remains uncertain or partially unknown, where very sparse measurement  ...  are approximated by convolutional filters while the nonlinear PDE functional is learned from neural networks (e.g., symbolic neural networks).  ... 
arXiv:2106.04781v1 fatcat:j3kacxwmerbhpeklrveqhw6jb4

Scalable algorithms for physics-informed neural and graph networks [article]

Khemraj Shukla, Mengjia Xu, Nathaniel Trask, George Em Karniadakis
2022 arXiv   pre-print
Such physics-informed machine learning integrates multimodality and multifidelity data with mathematical models, and implements them using neural networks or graph networks.  ...  Here, we review some of the prevailing trends in embedding physics into machine learning, using physics-informed neural networks (PINNs) based primarily on feed-forward neural networks and automatic differentiation  ...  The authors combined message passing neural networks with the method of lines and neural ODE (Chen et al., 2018) and obtained good results for advection-diffusion, heat equation and Burgers equation  ... 
arXiv:2205.08332v1 fatcat:3bq25a266vhyfhoommuj2uqtp4
« Previous Showing results 1 — 15 out of 693 results