Filters








28,557 Hits in 6.0 sec

Deep Set-to-Set Matching and Learning [article]

Yuki Saito, Takuma Nakamura, Hirotaka Hachiya, Kenji Fukumizu
2019 arXiv   pre-print
In this paper, we propose a deep learning architecture for the set-to-set matching that overcomes the above difficulties, including two novel modules: 1) a cross-set transformation and 2) cross-similarity  ...  The difficulties of set-to-set matching over ordinary data matching lie in the exchangeability in 1) set-feature extraction and 2) set-matching score; the pair of sets and the items in each set should  ...  However, to the best of our knowledge, studies using deep neural networks for matching two sets are non-existent.  ... 
arXiv:1910.09972v1 fatcat:wn3jvmpbjzcprkmt2k4ql2gmnm

A Dual Attentive Neural Network Framework with Community Metadata for Answer Selection [chapter]

Zhiqiang Liu, Mengzhang Li, Tianyu Bai, Rui Yan, Yan Zhang
2018 Lecture Notes in Computer Science  
We propose a novel dual attentive neural network framework (DANN) to embed question topics and user network structures for answer selection.  ...  The representation of questions and answers are first learned by convolutional neural networks (CNNs).  ...  Acknowledgment This work is supported by NSFC under Grant No.61532001 and No.61370054. We thank the three anonymous reviewers for their valuable comments.  ... 
doi:10.1007/978-3-319-73618-1_8 fatcat:2piwtxylbberbdyr7ayyw7rcvq

Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning [article]

Wenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Yang Gao, Jiebo Luo
2019 arXiv   pre-print
Specifically, building upon the recent episodic training mechanism, we propose a Deep Nearest Neighbor Neural Network (DN4 in short) and train it in an end-to-end manner.  ...  Our work leads to a simple, effective, and computationally efficient framework for few-shot learning.  ...  Illustration of the proposed Deep Nearest Neighbor Neural Network (DN4 in short) for a few-shot learning task in the 5-way and 1-shot setting.  ... 
arXiv:1903.12290v2 fatcat:yrft43dj2rbcpbvarsjdpm4uv4

A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks

Jeffrey Chan, Valerio Perrone, Jeffrey P Spence, Paul A Jenkins, Sara Mathieson, Yun S Song
2018 Advances in Neural Information Processing Systems  
In this work, we develop an exchangeable neural network that performs summary statistic-free, likelihood-free inference.  ...  To achieve this, two inferential challenges need to be addressed: (1) population data are exchangeable, calling for methods that efficiently exploit the symmetries of the data, and (2) computing likelihoods  ...  Acknowledgements We thank Ben Graham for helpful discussions and Yuval Simons for his suggestion to use the decile.  ... 
pmid:33244210 pmcid:PMC7687905 fatcat:ugwufqi7ijfetfrqjmb2kiznpm

BRUNO: A Deep Recurrent Model for Exchangeable Data [article]

Iryna Korshunova, Jonas Degrave, Ferenc Huszár, Yarin Gal, Arthur Gretton, Joni Dambre
2018 arXiv   pre-print
We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations.  ...  , few-shot learning, and anomaly detection.  ...  discussions, and Lionel Pigou for setting up the hardware.  ... 
arXiv:1802.07535v3 fatcat:2y7s2ojhdbgo7cm3fvdp2djzqu

A deep learning framework for football match prediction

Md. Ashiqur Rahman
2020 SN Applied Sciences  
An efficient framework is developed by deep neural networks (DNNs) and artificial neural network (ANNs) for predicting the outcomes of football matches.  ...  The outcome of this hypothesis can be derived that deep learning may be used for successfully predicting the outcomes of football matches or any other sporting events.  ...  Acknowledgements I would also like to show my gratitude to the Authors for sharing their pearls of wisdom with me during the course of this research, and I thank "anonymous" reviewers for their insights  ... 
doi:10.1007/s42452-019-1821-5 fatcat:emsn7afwhfdu5eoidsdbjrzh2e

Enhancing Multi-Robot Perception via Learned Data Association [article]

Nathaniel Glaser, Yen-Cheng Liu, Junjiao Tian, Zsolt Kira
2021 arXiv   pre-print
Specifically, each robot is in charge of locally encoding and decoding visual information, and an extensible neural mechanism allows for an uncertainty-aware and context-based exchange of intermediate  ...  To this end, we propose the Multi-Agent Infilling Network: an extensible neural architecture that can be deployed (in a distributed manner) to each agent in a robotic swarm.  ...  . • We propose an end-to-end learn-able Multi-Agent Infilling Network, MAIN, that (1) extracts spatial features for pairwise comparison, (2) leverages spatial context and matching uncertainty to produce  ... 
arXiv:2107.00769v1 fatcat:3fnqzee4ejampfeoee3l3oa5hu

Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks [article]

Dina Obeid, Hugo Ramambason, Cengiz Pehlevan
2019 arXiv   pre-print
In this paper, we introduce structured and deep similarity matching cost functions, and show how they can be optimized in a gradient-based manner by neural networks with local learning rules.  ...  These networks extend F\"oldiak's Hebbian/Anti-Hebbian network to deep architectures and structured feedforward, lateral and feedback connections.  ...  Acknowledgments We thank Alper Erdogan and Blake Bordelon for discussions. This work was supported by a gift from the Intel Corporation.  ... 
arXiv:1910.04958v2 fatcat:h4f7pwoeffcr7lz3i6xdmbvhlu

A survey on network intrusion detection system techniques

K. Nandha Kumar, S. Sukumaran
2018 International Journal of Advanced Technology and Engineering Exploration  
Conflicts of interest The authors have no conflicts of interest to declare.  ...  For evaluating network security and network attacks, the deep learning shows a promising effectiveness and gained prominence due to its increase in detection rate.  ...  The conventional machine learning methods are compared experimentally with four common deep learning methods like restricted Boltzmann machine (RBM), auto-encoders, recurrent neural network (RNN), and  ... 
doi:10.19101/ijatee.2018.546013 fatcat:lr6uh7abmrb6ppxwxhixpof57m

Deep Convolutional Network for Stereo Depth Mapping in Binocular Endoscopy

Xiong-zhi Wang, Yunfeng Nie, Shao-Ping Lu, Jingang Zhang
2020 IEEE Access  
Owing to the development of deep convolutional neural networks (CNNs), binocular depth estimation models have achieved many exciting results in the fields of autonomous driving and machine vision.  ...  layer deep CNNs method to generate real-time stereo depth mapping.  ...  DEEP LEARNING NETWORK The latest research on deep learning for disparity estimation focuses on how to accurately calculate the matching cost and how to post-optimize the disparity map.  ... 
doi:10.1109/access.2020.2987767 fatcat:522bhr4unfexlhuxo4zsfjoxbe

Credit Card Fraud Detection using Deep Learning based on Neural Network and Auto-encoder

2020 International Journal of Engineering and Advanced Technology  
This paper discusses the performance analysis and the comparative study of the two Deep Learning algorithms which include auto-encoder and the neural network.  ...  Thus, Artificial Intelligent (AI) algorithms are used to detect the behavior of such activity by learning the past behavior of the transaction of the users.  ...  Deep learning is a typical term for a neural network with numerous layers.  ... 
doi:10.35940/ijeat.e9934.069520 fatcat:67pmckkxhjecdhe56adttiutpe

A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks [article]

Jeffrey Chan, Valerio Perrone, Jeffrey P. Spence, Paul A. Jenkins, Sara Mathieson, Yun S. Song
2018 arXiv   pre-print
In this work, we develop an exchangeable neural network that performs summary statistic-free, likelihood-free inference.  ...  To achieve this, two inferential challenges need to be addressed: (1) population data are exchangeable, calling for methods that efficiently exploit the symmetries of the data, and (2) computing likelihoods  ...  YRI setting for the deep learning and LDhot method.  ... 
arXiv:1802.06153v2 fatcat:uv63a54qrfghzgotg5q3l2cv2a

A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks [article]

Jeffrey Chan, Valerio Perrone, Jeffrey P Spence, Paul A Jenkins, Sara Mathieson, Yun S Song
2018 bioRxiv   pre-print
In this paper, we learn the first exchangeable feature representation for population genetic data to work directly with genotype data.  ...  This is achieved by means of a novel Bayesian likelihood-free inference framework, where a permutation-invariant convolutional neural network learns the inverse functional relationship from the data to  ...  Acknowledgements We thank Ben Graham for helpful discussions and Yuval Simons for his suggestion to use the decile.  ... 
doi:10.1101/267211 fatcat:hofwzezsqfaybjrztesvjqe3ti

Deep Learning based Semantic Similarity Detection using Text Data

Muhammad Mansoor, Zahoor ur Rehman, Muhammad Shaheen, Muhammad Attique Khan, Mohamed Habib
2020 Information Technology and Control  
In this research, a novel approach is proposed using deep learning models, combining Long Short Term Memory network (LSTM) with Convolutional Neural Network (CNN) for measuring semantics similarity between  ...  Most of the similarity detection algorithms are based upon word to word matching, sentence/paragraph matching, and matching of the whole document.  ...  Given adequate information, deep neural networks are exhibited to be successful for a wide variety of machine learning tasks, including text learning tasks based on larger datasets.  ... 
doi:10.5755/j01.itc.49.4.27118 fatcat:lxmpb6d7wbfxjaoimvkvfn73ku

Conversation Engine for Deaf and Dumb

Monika K J
2021 International Journal for Research in Applied Science and Engineering Technology  
Deaf and hard hearing people use linguistic communication to exchange information between their own community and with others.  ...  Development of linguistic communication recognition application for deaf people is vital, as they'll be able to communicate easily with even people who don't understand language.  ...  Deep-learning architectures like deep neural networks, deep belief networks, graph neural networks, perennial neural networks and convolutional neural networks are applied to fields yet as pc vision, speech  ... 
doi:10.22214/ijraset.2021.36841 fatcat:pu4dckm5e5ft7npznebe2csl2m
« Previous Showing results 1 — 15 out of 28,557 results