Filters








19,450 Hits in 7.6 sec

Probabilistic Models for Local Patterns Analysis

Khiat Salim, Belbachir Hafida, Rahal Sid Ahmed
2014 Journal of Information Processing Systems  
An adequate choice for a probabilistic model can improve the quality of patterns that have been discovered.  ...  In such situations we propose the application of a probabilistic model in the synthesizing process.  ...  Graduation as a convergence of iterative maximum entropy The iterative scaling algorithm is well known in statistical literature as an technique which converges to the maximum entropy solution for problems  ... 
doi:10.3745/jips.2014.10.1.145 fatcat:htyowt3ipjd7jkbp3zok65xioe

Beyond independence: probabilistic models for query approximation on binary transaction data

D. Pavlov, H. Mannila, P. Smyth
2003 IEEE Transactions on Knowledge and Data Engineering  
In the maximum entropy method we treat itemsets as constraints on the distribution of the query variables and use the maximum entropy principle to build a joint probability model for the query attributes  ...  In particular, we introduce two techniques for building probabilistic models from frequent itemsets: the itemset maximum entropy method, and the itemset inclusion-exclusion model.  ...  Mixtures of Independence (Bernoulli) Models A probabilistic mixture model can be thought of as a generative model, i.e., a procedure for generating data under the assumption that it comes from AE different  ... 
doi:10.1109/tkde.2003.1245281 fatcat:vxb5h6cuoze47orum3zkchgceq

Generating Realistic Synthetic Population Datasets [article]

Hao Wu, Yue Ning, Prithwish Chakraborty, Jilles Vreeken, Nikolaj Tatti, Naren Ramakrishnan
2016 arXiv   pre-print
To generate such datasets over a large set of categorical variables, we propose the use of the maximum entropy principle to formalize a generative model such that in a statistically well-founded way we  ...  An efficient inference algorithm is designed to estimate the maximum entropy model, and we demonstrate how our approach is adept at estimating underlying data distributions.  ...  Acknowledgments Supported by the Intelligence Advanced Research Projects Activity (IARPA) via DoI/NBC contract number D12PC000337, the US Government is authorized to reproduce and distribute reprints of this work for  ... 
arXiv:1602.06844v3 fatcat:ut2xvumwz5d75mpzwcswaaoyzy

Generating Realistic Synthetic Population Datasets

Hao Wu, Yue Ning, Prithwish Chakraborty, Jilles Vreeken, Nikolaj Tatti, Naren Ramakrishnan
2018 ACM Transactions on Knowledge Discovery from Data  
To generate such datasets over a large set of categorical variables, we propose the use of the maximum entropy principle to formalize a generative model such that in a statistically well-founded way we  ...  An efficient inference algorithm is designed to estimate the maximum entropy model, and we demonstrate how our approach is adept at estimating underlying data distributions.  ...  Acknowledgments Supported by the Intelligence Advanced Research Projects Activity (IARPA) via DoI/NBC contract number D12PC000337, the US Government is authorized to reproduce and distribute reprints of this work for  ... 
doi:10.1145/3182383 fatcat:qlqxszi2ijgshffy3iuwokhv6q

Variational Bayesian inversion (VBI) of quasi-localized seismic attributes for the spatial distribution of geological facies

Muhammad Atif Nawaz, Andrew Curtis
2018 Geophysical Journal International  
Our mathematical model consists of seismic attributes as observed data, which are assumed to have been generated by the geological facies.  ...  Our method is computationally efficient, and is expected to be applicable to 3D models of realistic size on modern computers without incurring any significant computational limitations.  ...  Acknowledgements We are thankful to TOTAL UK for their sponsorship of this research.  ... 
doi:10.1093/gji/ggy163 fatcat:k3n3tsqq6nalfjfkoxbhe5f5n4

Valence Induction with a Head-Lexicalized PCFG [article]

Glenn Carroll, Mats Rooth
1998 arXiv   pre-print
Distributions are estimated using a modified EM algorithm. We evaluate the acquired lexicon both by comparison with a dictionary and by entropy measures.  ...  This paper presents an experiment in learning valences (subcategorization frames) from a 50 million word text corpus, based on a lexicalized probabilistic context free grammar.  ...  The memory requirements for a model generated from a 5M word segment are about 90Mbyte.  ... 
arXiv:cmp-lg/9805001v1 fatcat:pu3radbvxjehtl2nycyl4vvusu

A distributed learning framework for heterogeneous data sources

Srujana Merugu, Joydeep Ghosh
2005 Proceeding of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining - KDD '05  
We provide a mathematical formulation of the model integration problem using the maximum likelihood and maximum entropy principles and describe iterative algorithms that are guaranteed to converge to the  ...  We present a probabilistic model-based framework for distributed learning that takes into account privacy restrictions and is applicable to scenarios where the different sites have diverse, possibly overlapping  ...  convex optimization problems with linear constraints and can be solved efficiently using iterative scaling algorithms.  ... 
doi:10.1145/1081870.1081896 dblp:conf/kdd/MeruguG05 fatcat:5jq5ceburfftxjeu3xnqz4cdsu

Summarizing data succinctly with the most informative itemsets

Michael Mampaey, Jilles Vreeken, Nikolaj Tatti
2012 ACM Transactions on Knowledge Discovery from Data  
With this in mind, we introduce a well-founded approach for succinctly summarizing data with the most informative itemsets; using a probabilistic maximum entropy model, we iteratively find the itemset  ...  As we use the Maximum Entropy principle to obtain unbiased probabilistic models, and only include those itemsets that are most informative with regard to the current model, the summaries we construct are  ...  We employ the Maximum Entropy principle to build a probabilistic model of the data, use this model to iteratively identify the most surprising itemsets, and then update our model accordingly.  ... 
doi:10.1145/2382577.2382580 fatcat:ua57l4prpjfhli6dpmmrqugqn4

Quantification and segmentation of brain tissues from MR images: a probabilistic neural network approach

Yue Wang, T. Adah, Sun-Yuan Kung, Z. Szabo
1998 IEEE Transactions on Image Processing  
Index Terms-Finite mixture models, image segmentation, information theoretic criteria, model estimation, probabilistic neural networks, relaxation algorithm.  ...  This paper presents a probabilistic neural network based technique for unsupervised quantification and segmentation of brain tissues from magnetic resonance images.  ...  Food and Drug Administration, for their valuable input and guidance on this work.  ... 
doi:10.1109/83.704309 pmid:18172510 pmcid:PMC2171050 fatcat:iqhwaooehrbsraxeegf4xnfwvm

Probabilistic Models for Query Approximation with Large Sparse Binary Datasets [article]

Dmitry Y. Pavlov, Heikki Mannila, Padhraic Smyth
2013 arXiv   pre-print
In particular, we study a Markov random field (MRF) approach based on frequent sets and maximum entropy, and compare it to the independence model and the Chow-Liu tree model.  ...  We investigate the application of probabilistic models to this problem.  ...  Thus, on this figure we only report results for a sin gle "maximum entropy model" (since all 3 produce the same estimates, but using different computational methods).  ... 
arXiv:1301.3884v1 fatcat:v6kun4fi6nebxnfyawnve2wx7e

Tell me what i need to know

Michael Mampaey, Nikolaj Tatti, Jilles Vreeken
2011 Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '11  
With this in mind, we introduce a well-founded approach for succinctly summarizing data with a collection of itemsets; using a probabilistic maximum entropy model, we iteratively find the most interesting  ...  for describing the data.  ...  We employ the Maximum Entropy principle to build a probabilistic model of the data, use this model to iteratively identify the most surprising itemsets, and then update our model accordingly.  ... 
doi:10.1145/2020408.2020499 dblp:conf/kdd/MampaeyTV11 fatcat:xsblh64osvddlfo4r2gi4a3ete

Volumetric Next Best View by 3D Occupancy Mapping using Markov Chain Gibbs Sampler for Precise Manufacturing

Lei Hou, Xiaopeng Chen, Kunyan Lan, Rune Rasmussen, Jonathan Roberts.
2019 IEEE Access  
In this paper, we propose a model-free volumetric Next Best View (NBV) algorithm for accurate 3D reconstruction using a Markov Chain Monte Carlo method for high-mix-low-volume objects in manufacturing.  ...  The volumetric information gain based Next Best View algorithm can in real-time select the next optimal view that reveals the maximum uncertainty of the scanning environment with respect to a partially  ...  Merali for their technical support.  ... 
doi:10.1109/access.2019.2935547 fatcat:xpjiwsy5iffxvm3l3l3bhv46si

Dynamic Scale Inference by Entropy Minimization [article]

Dequan Wang, Evan Shelhamer, Bruno Olshausen, Trevor Darrell
2019 arXiv   pre-print
We propose a novel entropy minimization objective for inference and optimize over task and structure parameters to tune the model to each input.  ...  We extend dynamic scale inference from feedforward prediction to iterative optimization for further adaptivity.  ...  Acknowledgements We thank Anna Rohrbach for exceptionally generous feedback and editing help. We thank Kelsey Allen, Max Argus, and Eric Tzeng for their helpful comments on the exposition.  ... 
arXiv:1908.03182v1 fatcat:ffdbynzfnrdxlnldcnf4axtnqa

Model-Based Search for Combinatorial Optimization: A Critical Survey

Mark Zlochin, Mauro Birattari, Nicolas Meuleau, Marco Dorigo
2004 Annals of Operations Research  
In this paper we introduce model-based search as a unifying framework accommodating some recently proposed metaheuristics for combinatorial optimization such as ant colony optimization, stochastic gradient  ...  ascent, cross-entropy and estimation of distribution methods.  ...  More generally, this work was partially supported by the "Metaheuristics Network," a Research Training Network funded by the Improving Human Potential programme of the CEC, grant HPRN-CT-1999-00106.  ... 
doi:10.1023/b:anor.0000039526.52305.af fatcat:za5nmeiq7rchbdivrrr3bse6ha

Unsupervised Symbolization of Signal Time Series for Extraction of the Embedded Information

Yue Li, Asok Ray
2017 Entropy  
In general, a long time span at the fast scale is a tiny (i.e., several orders of magnitude smaller) interval at the slow scale.  ...  This paper formulates an unsupervised algorithm for symbolization of signal time series to capture the embedded dynamic behavior.  ...  predictive model via a finite-state automaton with probabilistic emission probabilities.  ... 
doi:10.3390/e19040148 fatcat:tvpocrnqyzadteriyqocozq4ni
« Previous Showing results 1 — 15 out of 19,450 results