1,726 Hits in 7.1 sec

The value of temporal data for learning of influence networks: A characterization via Kullback-Leibler divergence

Munther A. Dahleh, John N. Tsitsiklis, Spyros I. Zoumpoulis
2015 2015 54th IEEE Conference on Decision and Control (CDC)  
speed of learning of the correct hypothesis via the Kullback-Leibler divergence, under three different types of available data: knowing the set of entities who take a particular action; knowing the order  ...  We infer local influence relations between networked entities from data on outcomes and assess the value of temporal data by formulating relevant binary hypothesis testing problems and characterizing the  ...  ACKNOWLEDGMENTS This research was partially supported by the Air Force Office of Special Research (contract FA9550-09-1-0420). We are thankful to anonymous reviewers for useful suggestions.  ... 
doi:10.1109/cdc.2015.7402658 dblp:conf/cdc/DahlehTZ15 fatcat:c37hfq723bbp5b37dsst36mzbm

Variational Learning and Bits-Back Coding: An Information-Theoretic View to Bayesian Learning

A. Honkela, H. Valpola
2004 IEEE Transactions on Neural Networks  
The bits-back coding allows interpreting the cost function used in the variational Bayesian method called ensemble learning as a code length in addition to the Bayesian view of misfit of the posterior  ...  approximation and a lower bound of model evidence.  ...  ACKNOWLEDGMENT The authors would like to thank M. Harva and T. Östman for their help with the experiments. Additionally, they would like to thank J. Särelä, R. Vigário, and P.  ... 
doi:10.1109/tnn.2004.828762 pmid:15461074 fatcat:geffr4dhpncp3opa6ai4bizhim

Mining Divergent Opinion Trust Networks through Latent Dirichlet Allocation

N. Dokoohaki, M. Matskin
2012 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining  
Using a Twitter dataset we show that learned graphs exhibit properties of real-world like networks.  ...  We use the distributions resulting to model topics for generating social networks of group and individual users.  ...  In addition to lack of symmetry, a latter objection to using Kullback-Leibler as a metric is lack of normalization, as the resulting values might fall between any range of numbers.  ... 
doi:10.1109/asonam.2012.158 dblp:conf/asunam/DokoohakiM12 fatcat:jqa5jbgrhfdhdo7wafjouevvny

Attractor Metadynamics in Adapting Neural Networks [chapter]

Claudius Gros, Mathias Linkerhand, Valentin Walther
2014 Lecture Notes in Computer Science  
At any given time the network is characterized by a set of internal parameters, which are adapting continuously, albeit slowly.  ...  We study the nature of the metadynamics of the attractor landscape for several continuoustime autonomous model networks.  ...  Acknowledgments The authors would like to thank Peter Hirschfeld for illuminating suggestions.  ... 
doi:10.1007/978-3-319-11179-7_9 fatcat:rv6ow5jkvzae7c4kxnyvk26bee

Attractor Metadynamics in Adapting Neural Networks [article]

Claudius Gros, Mathias Linkerhand, Valentin Walther
2014 arXiv   pre-print
At any given time the network is characterized by a set of internal parameters, which are adapting continuously, albeit slowly.  ...  We study the nature of the metadynamics of the attractor landscape for several continuous-time autonomous model networks.  ...  Acknowledgments The authors would like to thank Peter Hirschfeld for illuminating suggestions.  ... 
arXiv:1404.5417v1 fatcat:ci7dqkzghjhofh5p4nanj354v4

Human interaction discovery in smartphone proximity networks

Trinh Minh Tri Do, Daniel Gatica-Perez
2011 Personal and Ubiquitous Computing  
The results show that the model can automatically discover a variety of social contexts. We objectively validated our model by studying its predictive and retrieval performance.  ...  Our analysis is conducted on Bluetooth data continuously sensed with smartphones for over one year from 40 individuals who are professionally or personally related.  ...  As scoring function for a given segmentation with n prominent users, we use Kullback Leibler divergence between a prototype distribution with n users and the input distribution.  ... 
doi:10.1007/s00779-011-0489-7 fatcat:ygurpohnyfen3nafxuwgcdaycm

DeepAuto: A Hierarchical Deep Learning Framework for Real-Time Prediction in Cellular Networks [article]

Abhijeet Bhorkar, Ke Zhang, Jin Wang
2019 arXiv   pre-print
It further merge with feed-forward networks to learn the impact of network configurations and other external factors.  ...  We validate the approach by predicting two important KPIs, including cell load and radio channel quality, using large-scale real network streaming measurement data from the operator.  ...  We use Kullback-Leibler (KL) divergence as a loss metric for comparing true and predicted distribution.  ... 
arXiv:2001.01553v1 fatcat:6nogrl55aff4xjo6f454xqmrei

The Kidneys Are Not All Normal: Investigating the Speckle Distributions of Transplanted Kidneys [article]

Rohit Singla, Ricky Hu, Cailin Ringstrom, Victoria Lessoway, Janice Reid, Christopher Nguan, Robert Rohling
2022 arXiv   pre-print
While both had excellent goodness of fit, the Nakagami had higher Kullbeck-Leibler divergence.  ...  This is especially true for the regions of the transplanted kidney: the cortex, the medulla and the central echogenic complex.  ...  Acknowledgements The authors acknowledge funding from the Natural Sciences and Engineering Research Council of Canada as well as the Kidney Foundation of Canada.  ... 
arXiv:2206.06654v1 fatcat:ufmprcjq45gr7fnjqtstvir2vy

Mod-DeepESN: Modular Deep Echo State Network [article]

Zachariah Carmichael, Humza Syed, Stuart Burtner, Dhireesha Kudithipudi
2019 arXiv   pre-print
It outperforms state-of-the-art for time series prediction tasks.  ...  The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems.  ...  Acknowledgments The authors would like to thank the members of the RIT Neuromorphic AI Lab for their valuable feedback on this work.  ... 
arXiv:1808.00523v2 fatcat:bknwdoxivncybnrp3zm3rcz7cq

Detecting Algorithmically Generated Domain-Flux Attacks With DNS Traffic Analysis

Sandeep Yadav, Ashwath Kumar Krishna Reddy, A. L. Narasimha Reddy, Supranamaya Ranjan
2012 IEEE/ACM Transactions on Networking  
We train by using a good data set of domains obtained via a crawl of domains mapped to all IPv4 address space and modeling bad data sets based on behaviors seen so far and expected.  ...  Recent Botnets such as Conficker, Kraken and Torpig have used DNS based "domain fluxing" for command-and-control, where each Bot queries for existence of a series of domain names and the owner has to register  ...  Metrics for anomaly detection The K-L(Kullback-Leibler) divergence metric is a nonsymmetric measure of "distance" between two probability distributions.  ... 
doi:10.1109/tnet.2012.2184552 fatcat:qddkctibhnc2llpyow6bjeqsbq

CECAV-DNN: Collective Ensemble Comparison and Visualization using Deep Neural Networks

Wenbin He, Junpeng Wang, Hanqi Guo, Han-Wei Shen, Tom Peterka
2020 Visual Informatics  
A B S T R A C T We propose a deep learning approach to collectively compare two or multiple ensembles, each of which is a collection of simulation outputs.  ...  For example, in developing a new simulation model, scientists often interested in how the model performs compared with old models such that scientists can have a better understanding of the new model and  ...  Acknowledgments This work was supported in part by US Department of Energy Los Alamos National Laboratory contract 47145 and UT-Battelle LLC contract 4000159447 program manager Laura Biven.  ... 
doi:10.1016/j.visinf.2020.04.004 fatcat:fzo6yn5ymnbwpmebirgw6c4fwa

Integrative Bayesian analysis of brain functional networks incorporating anatomical knowledge

Ixavier A. Higgins, Suprateek Kundu, Ying Guo
2018 NeuroImage  
We propose a hierarchical Bayesian Gaussian graphical modeling approach which models the brain functional networks via sparse precision matrices whose degree of edge specific shrinkage is a random variable  ...  This calls for the development of advanced network modeling tools that appropriately incorporate anatomical structure in constructing brain functional networks.  ...  Acknowledgements The authors would like to thank the referees for insightful comments on the model formulation and application.  ... 
doi:10.1016/j.neuroimage.2018.07.015 pmid:30017786 pmcid:PMC6139051 fatcat:4er2ms5agnappcy2f6kgbws7ki

Information diffusion network inferring and pathway tracking

DongHao Zhou, WenBao Han, YongJun Wang, BaoDi Yuan
2015 Science China Information Sciences  
We use blocked coordinate descent method to learn a sparse estimation of the latent network.  ...  Network diffusion, such as spread of ideas, rumors, contagious disease, or a new type of behaviors, is one of the fundamental processes within networks.  ...  and fund from the State Key Laboratory of Mathematical Engineering and Advanced Computing of China. We would like to thank the anonymous referees for their help in improving this paper.  ... 
doi:10.1007/s11432-015-5288-8 fatcat:zpiwrr4x5jhhji2onjxx5buro4

Game of GANs: Game-Theoretical Models for Generative Adversarial Networks [article]

Monireh Mohebbi Moghadam, Bahar Boroomand, Mohammad Jalali, Arman Zareian, Alireza DaeiJavad, Mohammad Hossein Manshaei, Marwan Krunz
2022 arXiv   pre-print
Generative Adversarial Networks (GANs) have recently attracted considerable attention in the AI community due to its ability to generate high-quality data of significant statistical resemblance to real  ...  Fundamentally, GAN is a game between two neural networks trained in an adversarial manner to reach a zero-sum Nash equilibrium profile.  ...  Unlike [68] , Nguyen et al. in [72] combined the Kullback-Leibler (KL) and reverse KL divergence (the measure of how one probability distribution is different from a second) into a unified objective  ... 
arXiv:2106.06976v3 fatcat:mecyjeopxnesjfj7bcoiim3p3a

Periodic fluctuations in correlation-based connectivity density time series: Application to wind speed-monitoring network in Switzerland

Mohamed Laib, Luciano Telesca, Mikhail Kanevski
2018 Physica A: Statistical Mechanics and its Applications  
In this paper, we study the periodic fluctuations of connectivity density time series of a wind speed-monitoring network in Switzerland.  ...  The intensity of such annual periodic oscillations is larger for lower correlation thresholds and smaller for higher.  ...  For each wind speed time series and for each of the three distributions we calculated the Kullback-Leibler divergence (KLD), which is known as the entropy between two density functions [32] .  ... 
doi:10.1016/j.physa.2017.11.081 fatcat:wueiramzorelrobma3faoxgule
« Previous Showing results 1 — 15 out of 1,726 results