Filters








430,234 Hits in 3.2 sec

Recurrent Relational Networks [article]

Rasmus Berg Palm, Ulrich Paquet, Ole Winther
2018 arXiv   pre-print
Using Pretty-CLEVR, we probe the limitations of multi-layer perceptrons, relational and recurrent relational networks.  ...  We introduce the recurrent relational network, a general purpose module that operates on a graph representation of objects.  ...  Recurrent Relational Networks We ground the discussion of a recurrent relational network in something familiar, solving a Sudoku puzzle.  ... 
arXiv:1711.08028v4 fatcat:tpgf65dhqrderfwfvthns72udq

Relational recurrent neural networks [article]

Adam Santoro, Ryan Faulkner, David Raposo, Jack Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy Lillicrap
2018 arXiv   pre-print
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods.  ...  ., tasks involving relational reasoning.  ...  reasoning in recurrent neural networks.  ... 
arXiv:1806.01822v2 fatcat:civthbeomzhixprxchbry33luq

Relation Classification via Recurrent Neural Network [article]

Dongxu Zhang, Dong Wang
2015 arXiv   pre-print
In this paper, we propose a simple framework based on recurrent neural networks (RNN) and compare it with CNN-based model.  ...  Deep learning has gained much success in sentence-level relation classification.  ...  In this paper, we propose a simple framework based on recurrent neural networks (RNN) and compare it with CNN-based model.  ... 
arXiv:1508.01006v2 fatcat:gcaxzbd35neatg6twznxxta3zq

A Recurrent Graph Neural Network for Multi-Relational Data [article]

Vassilis N. Ioannidis, Antonio G. Marques, Georgios B. Giannakis
2019 arXiv   pre-print
In this paper, we introduce a graph recurrent neural network (GRNN) for scalable semi-supervised learning from multi-relational data.  ...  Key aspects of the novel GRNN architecture are the use of multi-relational graphs, the dynamic adaptation to the different relations via learnable weights, and the consideration of graph-based regularizers  ...  Albeit their ubiquitous presence, development of SSL methods that account for multi-relational networks is only in its infancy, see, e.g., [1, 3] . Related work.  ... 
arXiv:1811.02061v3 fatcat:lcjdu4s7jffkjjtwzh6odqprli

Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks [article]

Rajarshi Das, Arvind Neelakantan, David Belanger, Andrew McCallum
2017 arXiv   pre-print
Our goal is to combine the rich multistep inference of symbolic logical reasoning with the generalization capabilities of neural networks.  ...  (3) we learn to share strength in a single RNN that represents logical composition across all relations.  ...  Reasoning is performed nonatomically about conjunctions of relations in an arbitrary length path by composing them with a recurrent neural network (RNN).  ... 
arXiv:1607.01426v3 fatcat:2ty3lxyldbeadajgbx6fuuhqle

Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations [article]

Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, Xudong Liu
2020 arXiv   pre-print
As a solution, we design a multi-task learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features  ...  networks for prediction.  ...  Model In this section, we describe the recurrent interaction network (RIN) for extracting relational facts in text.  ... 
arXiv:2005.00162v2 fatcat:6ihbmzlswjemtbvdbiasx2t6ne

Recurrent Relational Memory Network for Unsupervised Image Captioning

Dan Guo, Yang Wang, Peipei Song, Meng Wang
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In this paper, we propose a novel memory-based network rather than GAN, named Recurrent Relational Memory Network (R2M).  ...  memories, correlating the relational reasoning between common visual concepts and the generated words for long periods.  ...  Orthogonal to above GAN-based models, in this paper, we propose a novel memory-based solution, named Recurrent Relational Memory Network (R 2 M ).  ... 
doi:10.24963/ijcai.2020/128 dblp:conf/ijcai/GuoWSW20 fatcat:ttv3qb2kw5fyjatm3fknc25uk4

Recurrent Relational Memory Network for Unsupervised Image Captioning [article]

Dan Guo, Yang Wang, Peipei Song, Meng Wang
2020 arXiv   pre-print
In this paper, we propose a novel memory-based network rather than GAN, named Recurrent Relational Memory Network (R^2M).  ...  memories, correlating the relational reasoning between common visual concepts and the generated words for long periods.  ...  Figure 2 : 2 An overview of R 2 M (Recurrent Relational Memory network) Figure 3 : 3 Memory mechanism in R 2 M.Decoder.  ... 
arXiv:2006.13611v1 fatcat:w5uwfq6tknevzin2zoxj5gpgy4

Bidirectional Recurrent Convolutional Neural Network for Relation Classification

Rui Cai, Xiaodong Zhang, Houfeng Wang
2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We further explore how to make full use of the dependency relations information in the SDP, by combining convolutional neural networks and twochannel recurrent neural networks with long short term memory  ...  Some state-of-the-art systems concentrate on modeling the shortest dependency path (SDP) between two entities leveraging convolutional or recurrent neural networks.  ...  The NN research for relation classification has centered around two main network architectures: convolutional neural networks and recursive/recurrent neural networks.  ... 
doi:10.18653/v1/p16-1072 dblp:conf/acl/CaiZW16 fatcat:cflgpg7zefflnaqrdov5qkxbhq

Relational Recurrent Neural Networks For Vehicle Trajectory Prediction

Kaouther Messaoud, Itheri Yahiaoui, Anne Verroust-Blondet, Fawzi Nashashibi
2019 2019 IEEE Intelligent Transportation Systems Conference (ITSC)  
Knowing the performance of Long Short Term Memories (LSTMs) in sequence modeling and the power of attention mechanism to capture long range dependencies, we bring relational recurrent neural networks (  ...  The originality of this network is that it combines the advantages of the LSTM blocks in representing the temporal evolution of trajectories and the attention mechanism to model the relative interactions  ...  The proposed architecture is based on Relational Recurrent Neural Networks (RRNNs) [13] encoder decoder.  ... 
doi:10.1109/itsc.2019.8916887 dblp:conf/itsc/MessaoudYVN19 fatcat:t37h24wjsjg4njvv63lap75gcm

Structure Regularized Bidirectional Recurrent Convolutional Neural Network for Relation Classification [article]

Ji Wen
2017 arXiv   pre-print
In this paper, we present a novel model, Structure Regularized Bidirectional Recurrent Convolutional Neural Network(SR-BRCNN), to classify the relation of two entities in a sentence, and the new dataset  ...  Some state-of-the-art systems concentrate on modeling the shortest dependency path (SDP) between two entities leveraging convolutional or recurrent neural networks.  ...  A number of convolutional neural network (CNN), recurrent neural network (RNN), and other neural architectures have been proposed for relation classification.  ... 
arXiv:1711.02509v1 fatcat:wnehk2vemnd5vgo2h7gdwe23eu

A Latent Variable Recurrent Neural Network for Discourse Relation Language Models [article]

Yangfeng Ji and Gholamreza Haffari and Jacob Eisenstein
2016 arXiv   pre-print
This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences.  ...  A recurrent neural network generates individual words, thus reaping the benefits of discriminatively-trained vector representations.  ...  Discourse relations z t are treated as latent variables, which are linked with a recurrent neural network over words in a latent variable recurrent neural network (Chung et al., 2015) .  ... 
arXiv:1603.01913v2 fatcat:4bsf55cb6rfxrnivsqwynenu3u

Recurrent Dirichlet Belief Networks for Interpretable Dynamic Relational Data Modelling [article]

Yaqiong Li, Xuhui Fan, Ling Chen, Bin Li, Zheng Yu, Scott A. Sisson
2020 arXiv   pre-print
We apply the Recurrent-DBN to dynamic relational data problems.  ...  In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable  ...  In this work, we propose a Recurrent Dirichlet Belief Network (Recurrent-DBN) to explore the complex latent structures in dynamic relational data.  ... 
arXiv:2002.10235v2 fatcat:puruxwpcbffr5cnocl7xbhyotq

Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition [article]

Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori
2016 arXiv   pre-print
Instead of using a traditional inference method, we use a sequential inference modeled by a recurrent neural network.  ...  Rich semantic relations are important in a variety of visual recognition problems.  ...  This network structure is a recurrent neural network (RNN).  ... 
arXiv:1511.04196v2 fatcat:xlhcepz44jfuxmwo6rc6tf3ckq

Character-based recurrent neural networks for morphological relational reasoning

Olof Mogren, Richard Johansson
2017 Proceedings of the First Workshop on Subword and Character Level Models in NLP  
To address the task of predicting a word form given a demo relation (a pair of word forms) and a query word, we devise a character-based recurrent neural network architecture using three separate encoders  ...  We present a model for predicting word forms based on morphological relational reasoning with analogies.  ...  Recurrent neural networks A recurrent neural network (RNN) is an artificial neural network that can model a sequence of arbitrary length.  ... 
doi:10.18653/v1/w17-4108 dblp:conf/emnlp/MogrenJ17 fatcat:227sbxy53ncgrpxcbek3wdjm4u
« Previous Showing results 1 — 15 out of 430,234 results