A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
A simple neural network module for relational reasoning
[article]
2017
arXiv
pre-print
Preserved Fulltext
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. ...
In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. ...
Acknowledgments We would like to thank Murray Shanahan, Ari Morcos, Scott Reed, Daan Wierstra, Alex Lerchner, and many others on the DeepMind team, for critical feedback and discussions. ...
arXiv:1706.01427v1
fatcat:t7tycni3rndfdl4ofhux4vr2a4
Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module
2018
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
During the last years, there has been a lot of interest in achieving some kind of complex reasoning using deep neural networks. ...
To solve these issues, we introduce the Working Memory Network, a MemNN architecture with a novel working memory storage and reasoning module. ...
To do that we pass the output through a simple neural network f t . ...
doi:10.18653/v1/p18-1092
dblp:conf/acl/PavezAA18
fatcat:ecc2tayjljgcrhygazxajpu244
Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
During the last years, there has been a lot of interest in achieving some kind of complex reasoning using deep neural networks. ...
To solve these issues, we introduce the Working Memory Network, a MemNN architecture with a novel working memory storage and reasoning module. ...
To do that we pass the output through a simple neural network f t . ...
arXiv:1805.09354v1
fatcat:qzqlac5tzfbsnbj6o5vq6mtqey
Dilated DenseNets for Relational Reasoning
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Despite their impressive performance in many tasks, deep neural networks often struggle at relational reasoning. ...
In this extended abstract, we show that a DenseNet incorporating dilated convolutions excels at relational reasoning on the Sort-of-CLEVR dataset, allowing us to forgo this relational module and its associated ...
A simple neural network module for relational reasoning. ...
arXiv:1811.00410v1
fatcat:njsdwionurdyvgsfmmooyya2uu
Neural Module Networks
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We describe a procedure for constructing and learning *neural module networks*, which compose collections of jointly-trained neural "modules" into deep networks for question answering. ...
We evaluate our approach on two challenging datasets for visual question answering, achieving state-of-the-art results on both the VQA natural image dataset and a new dataset of complex questions about ...
Acknowledgments The authors are grateful to Lisa Anne Hendricks, Eric Tzeng, and Russell Stewart for useful conversations, and to Nvidia for a hardware grant. ...
arXiv:1511.02799v4
fatcat:4lrnuh4tafdevcl3ixcmxqufvi
What Can Neural Networks Reason About?
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Neural networks have succeeded in many reasoning tasks. ...
Empirically, these tasks require specialized network structures, e.g., Graph Neural Networks (GNNs) perform well on many such tasks, but less structured networks fail. ...
PRELIMINARIES We begin by introducing notations and summarizing common neural networks for reasoning tasks. Let S denote the universe, i.e., a configuration/set of objects to reason about. ...
arXiv:1905.13211v4
fatcat:qvuc7uncovfjhdbgzaajxgkyfu
Toward Accurate Visual Reasoning With Dual-Path Neural Module Networks
2020
Frontiers in Robotics and AI
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The recently proposed neural module network (Andreas et al., 2016b), which assembles the model with a few primitive modules, is capable of performing a spatial or arithmetical reasoning over the input ...
To address these issues, we propose a novel method of Dual-Path Neural Module Network which can implement complex visual reasoning by forming a more flexible layout regularized by the pairwise loss. ...
of composing a new deep network with neural modules for each given input. ...
doi:10.3389/frobt.2020.00109
pmid:33501276
pmcid:PMC7805672
fatcat:4p6abhbp4vhlninrbgdy2bg6xu
RelNet: End-to-End Modeling of Entities & Relations
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We introduce RelNet: a new model for relational reasoning. ...
RelNet is a memory augmented neural network which models entities as abstract memory slots and is equipped with an additional relational memory which models relations between all memory pairs. ...
They demonstrated that simple neural network modules are not as effective at relational reasoning and their proposed module is similar to our model. ...
arXiv:1706.07179v2
fatcat:gv4tx6ecdja2fiem6fztl25oau
Learning to Compose Neural Networks for Question Answering
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. ...
Parameters for these modules are learned jointly with network-assembly parameters via reinforcement learning, with only (world, question, answer) triples as supervision. ...
Acknowledgments JA is supported by a National Science Foundation Graduate Fellowship. MR is supported by a fellowship within the FIT weltweit-Program of the German Academic Exchange Service (DAAD). ...
arXiv:1601.01705v4
fatcat:kt2skogwirerpny37poacfr2e4
Learning to Compose Neural Networks for Question Answering
2016
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. ...
Our approach, which we term a dynamic neural module network, achieves state-of-theart results on benchmark datasets in both visual and structured domains. ...
Acknowledgments JA is supported by a National Science Foundation Graduate Fellowship. MR is supported by a fellowship within the FIT weltweit-Program of the German Academic Exchange Service (DAAD). ...
doi:10.18653/v1/n16-1181
dblp:conf/naacl/AndreasRDK16
fatcat:n5hnyyiuafaohl24qeybjpgzbi
FigureNet: A Deep Learning model for Question-Answering on Scientific Plots
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our approach outperforms the state-of-the-art Relation Networks baseline by approximately 7% on this dataset, with a training time that is over an order of magnitude lesser. ...
In this work, we describe a deep learning model that addresses the reasoning task of question-answering on categorical plots. ...
Relation Networks Relation networks(RN) were introduced by [10] as a simple yet powerful neural module for relational reasoning. ...
arXiv:1806.04655v2
fatcat:okpc5v6krzfmjoxuas7b3nnvvi
Predicting the Popularity of Online Videos via Deep Neural Networks
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose a general prediction model using the multi-task learning (MTL) module and the relation network (RN) module, where MTL can reduce over-fitting and RN can model the relations of ...
Predicting the popularity of online videos is important for video streaming content providers. This is a challenging problem because of the following two reasons. ...
An RN is a simple and effective module for the case when input "objects" (usually hidden units of a neural network) have relations which each other. ...
arXiv:1711.10718v2
fatcat:3zxjlnijkbforll4spg3vjkn4y
KANDINSKYPatterns – An experimental exploration environment for Pattern Analysis and Machine Intelligence
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
There is still a significant gap between machine-level pattern recognition and human-level concept learning. ...
Humans can learn under uncertainty from only a few examples and generalize these concepts to solve new problems. ...
ACKNOWLEDGEMENTS This work has received funding by the Austrian Science Fund (FWF), Project: P-32554 "A reference model for explainable Artificial Intelligence in the medical domain". ...
arXiv:2103.00519v1
fatcat:d57pwgzf4vhmpaa5hqwm7ls5zq
Graph Neural Networks with Generated Parameters for Relation Extraction
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Among existing models, graph neural networks (GNNs) is one of the most effective approaches for multi-hop relational reasoning. ...
In this paper, we propose to generate the parameters of graph neural networks (GP-GNNs) according to natural language sentences, which enables GNNs to process relational reasoning on unstructured text ...
For example, Santoro et al. (2017) propose a simple neural network to reason the relationship of objects in a picture, Xu et al. (2017) build up a scene graph according to an image, and (Kipf et al ...
arXiv:1902.00756v1
fatcat:lpnbujhf4nd5hdu7iltiif7jwu
Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Concretely, we design an adversarial graph network that interpolates a symbolic graph reasoning module into a generative adversarial network through embedding prior domain knowledge, achieving semantic ...
In this paper, we propose the neural-symbolic learning (NSL) framework that performs human-like learning by unifying deep neural learning and symbolic logical reasoning for the spinal medical report generation ...
In this paper, we propose a new graph reasoning module for capturing the relations between spinal structures and improving the high-level semantic representation. ...
arXiv:2004.13577v1
fatcat:oh5aka5zr5be3ipd7qqnyhikzy
« Previous
Showing results 1 — 15 out of 127,282 results