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.
Filters
DeepDPM: Dynamic Population Mapping via Deep Neural Network
[article]
2018
arXiv
pre-print
Preserved Fulltext
Other Versions
In DeepDPM, we utilize super-resolution convolutional neural network(SRCNN) based model to directly map coarse data into higher resolution data, and a time-embedded long short-term memory model to effectively ...
In this paper, we first propose the idea to generate dynamic population distributions in full-time series, then we design dynamic population mapping via deep neural network(DeepDPM), a model that describes ...
In this paper, we propose DeepDPM, a deep learning based model that consists of augmented stacked superresolution convolution neural network(SRCNN) as the static part, and time-embedded LSTM as the dynamic ...
arXiv:1811.02644v2
fatcat:6iugvt2vvfeatpt43jdmwgrkoi
DeepDPM: Dynamic Population Mapping via Deep Neural Network
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
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.
In DeepDPM, we utilize super-resolution convolutional neural network(SRCNN) based model to directly map coarse data into higher resolution data, and a timeembedded long short-term memory model to effectively ...
In this paper, we first propose the idea to generate dynamic population distributions in full-time series, then we design dynamic population mapping via deep neural network(DeepDPM), a model that describes ...
In this paper, we propose DeepDPM, a deep learning based model that consists of augmented stacked superresolution convolution neural network(SRCNN) as the static part, and time-embedded LSTM as the dynamic ...
doi:10.1609/aaai.v33i01.33011294
fatcat:vx5ql3xrnfh5zo2mwg7yidf45y
Adaptive connectionist systems for engineering applications
2013
Evolving Systems
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 2017; you can also visit the original URL.
The file type is application/pdf.
While most existing approaches develop static ANN models optimal only under specific conditions, this work suggests a dynamic flexible and adjustable neural spatiotemporal model. ...
The authors combine a generalized intrinsic plasticity rule with a local information dynamics based schema of reservoir neuron leak adaptation. ...
While most existing approaches develop static ANN models optimal only under specific conditions, this work suggests a dynamic flexible and adjustable neural spatiotemporal model. ...
doi:10.1007/s12530-013-9100-y
fatcat:m57fqzkmvvhyjg5xya5mr7rvje
A Survey on Video Classification Methods Based on Deep Learning
2019
DEStech Transactions on Computer Science and Engineering
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.
With the development of multimedia and communication technology, the amount of multimedia data, for example, video data has been rapidly emerging. ...
How to process these data accurately and efficiently has attracted more and more researchers' attention. Video classification is an important part of video data processing. ...
As the name implies, the 3D convolutional neural network extends the convolutional neural network into a 3-dimensional space, which stacks several frames into a cube, and uses a 3D convolution kernel in ...
doi:10.12783/dtcse/cisnrc2019/33301
fatcat:fbvt4nxfe5bdleh4mocyoopzzy
Identifying critical nodes in temporal networks by network embedding
2020
Scientific Reports
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.
temporal networks into regression problem by the algorithm. ...
Critical nodes in temporal networks play more significant role than other nodes on the structure and function of networks. ...
. we convert the critical node identification problem in temporal networks into regression problem by the algorithm. ...
doi:10.1038/s41598-020-69379-z
pmid:32719327
fatcat:xf3agsvzrvhoxkoikrnkdhu6i4
A Survey on Embedding Dynamic Graphs
[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.
Other Versions
We introduce the formal definition of dynamic graph embedding, focusing on the problem setting and introducing a novel taxonomy for dynamic graph embedding input and output. ...
Embedding static graphs in low-dimensional vector spaces plays a key role in network analytics and inference, supporting applications like node classification, link prediction, and graph visualization. ...
Moreover, this paper is dedicated to the memory of our dear co-worker Artur Ziviani, who passed away while this paper was being peer-reviewed. Artur was a brilliant researcher and dedicated advisor. ...
arXiv:2101.01229v2
fatcat:lqjkkksn45g7beizhcstakf6ry
Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
2021
IEEE Access
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.
Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. ...
Dynamic networks are used in a wide range of fields, including social network analysis, recommender systems and epidemiology. ...
Any kind of node dynamics can be combined with any kind of link duration network. We can thus have, a growing evolving network or a node-static temporal network. ...
doi:10.1109/access.2021.3082932
fatcat:4pbp2kn6ovf65pnm5pbv7idpim
Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
[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
We contribute: (i) a comprehensive dynamic network taxonomy, (ii) a survey of dynamic graph neural networks and (iii) an overview of how dynamic graph neural networks can be used for dynamic link prediction ...
Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. ...
Dynamic graph neural networks combine deep time series encoding with aggregation of neighbouring nodes. Often discrete versions of these models take the form of a combination of a GNN and an RNN. ...
arXiv:2005.07496v1
fatcat:ditdpefszzd6bfh4enbcdkztna
Time in Connectionist Models
[chapter]
2000
Lecture Notes in Computer Science
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 2017; you can also visit the original URL.
The file type is application/pdf.
Henderson, the reviewers and editors for their helpful comments on this chapter, and Peter Weyer-Brown for his careful proofreading of the manuscript. ...
generalization of estimator standard static networks continuous mapping AR RNNs dynamical system/Turing Machine ARMA spiking neural networks Turing machine any? ...
network being transcoded into a set of timings of a spiking neural network. ...
doi:10.1007/3-540-44565-x_6
fatcat:3ikjpjv2rvhhll6hcqexew7kmq
Adjoint-operators and non-adiabatic learning algorithms in neural networks
1991
Applied Mathematics Letters
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.
., forward in time) with the dynamics of a nonlinear neural network. ...
These equations provide the foundations for a new methodology which enables the implementation of temporal learning algorithms in a highly efficient manner. ...
with dynamical neural networks, while achieving a dramatic reduction in the overall computational costs. ...
doi:10.1016/0893-9659(91)90172-r
fatcat:nbz5a65hfvdhlp26v2kklv5jle
Robust Pose Transfer with Dynamic Details using Neural Video Rendering
[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.
Other Versions
To be specific, a novel texture representation is presented to encode both the static and pose-varying appearance characteristics, which is then mapped to the image space and rendered as a detail-rich ...
Overall, we propose a neural video rendering framework coupled with an image-translation-based dynamic details generation network (D2G-Net), which fully utilizes both the stability of explicit 3D features ...
Specifically, rather than using a traditional static RGB-channel image, we represent the texture with a hybrid feature map, which encodes the static RGB colors explicitly and the dynamic details of human ...
arXiv:2106.14132v2
fatcat:dslhnmaborfstasn2qh6lwejly
Guest Editorial: Data-Driven Management of Complex Systems Through Plant-Wide Performance Supervision
2021
IEEE Transactions on Industrial Informatics
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.
The proposed deep double-supervised embedding neural network consisted of two supervised deep neural networks: A deep class centered uniform distribution neural network which mapped the high-dimensional ...
The proposed network took into account both temporal dependence and channel connection. ...
doi:10.1109/tii.2020.3023259
fatcat:2x44ydldbreqdcyejz5jui7q24
Dynamic Gesture Recognition Based on MEMP Network
2019
Future Internet
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.
Because each kind of neural network structure has its limitation, we proposed a neural network with alternate fusion of 3D CNN and ConvLSTM, which we called the Multiple extraction and Multiple prediction ...
The main feature of the MEMP network is to extract and predict the temporal and spatial feature information of gesture video multiple times, which enables us to obtain a high accuracy rate. ...
Neural networks are often used in combination when recognizing the video data set of gestures. In the combination of CNN and LSTM, videos are firstly divided into a set of frames with fixed length. ...
doi:10.3390/fi11040091
fatcat:gcbeesljhbeovor6pj2vigfzaa
On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)
2020
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
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.
data) and a term due to overfitting (additional suboptimality due to limited data). ...
When an agent has limited information on its environment, the suboptimality of an RL algorithm can be decomposed into the sum of two terms: a term related to an asymptotic bias (suboptimality with unlimited ...
After that, they used deep neural networks to map audio content to those latent factors. ...
doi:10.24963/ijcai.2020/695
dblp:conf/ijcai/0001Z20
fatcat:yx2wihhuobgmjjh4aevkbr33g4
Advances in dynamic temporal networks: Understanding the temporal dynamics of complex adaptive networks
2013
The European Physical Journal Special Topics
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 2016; you can also visit the original URL.
The file type is application/pdf.
However, research on the temporal dynamics of complex networks is largely a new territory yet to map out. ...
The theory of complex networks The development of the theory of complex networks (including social networks and systems from other domains) has been in the foreground of interest in the past decade. a ...
PMAS also acknowledges the support from a grant from the "Leading Scientist Program" of the Government of the Russian Federation, under contract 11.G34.31.0019 and the support from the FET-Proactive grant ...
doi:10.1140/epjst/e2013-01926-8
fatcat:et2pqoatm5ebnfrnehtbpb77uy
« Previous
Showing results 1 — 15 out of 29,769 results