192,512 Hits in 3.4 sec

Support vector machine based on hierarchical and dynamical granulation

Husheng Guo, Wenjian Wang
2016 Neurocomputing  
This paper presents an improved granular support vector machine learning model based on hierarchical and dynamical granulation, namely, HD_GSVM, to solve the low learning efficiency and generalization  ...  Finally, the decision hyperplane will be obtained through all of the granules at different hierarchical and dynamical granulation levels effectively.  ...  Support vector machine based on hierarchical and dynamical granulation At present, most studies of GSVM concentrate on statistic granulation, but studies on the hierarchical and dynamical granulation method  ... 
doi:10.1016/j.neucom.2015.10.136 fatcat:ums4wlip6vdihk4swtddqu3uyy

Slow Dynamics Due to Singularities of Hierarchical Learning Machines

Hyeyoung Park, Masato Inoue, Masato Okada
2005 Progress of Theoretical Physics Supplement  
Recently, slow dynamics in learning of neural networks has been known to be closely related to singularities, which exist in parameter spaces of hierarchical learning models.  ...  To show the influence of singular structure on learning dynamics, we take statistical mechanical approaches and investigate online-learning dynamics under various learning scenario with different relationship  ...  and learning dynamics. 1), 3) Even though many statistical mechanical analysis on the slow learning dynamics have been done, 2), 5), 6) the singular structure and its influence on learning dynamics  ... 
doi:10.1143/ptps.157.275 fatcat:zff5ioeifvbf7jgylg6syfo4fq

Diagnosability Analysis of a Class of Hierarchical State Machines

Andrea Paoli, Stéphane Lafortune
2008 Discrete event dynamic systems  
This paper addresses the problem of Fault Detection and Isolation for a particular class of discrete event dynamical systems called Hierarchical Finite State Machines (HFSMs).  ...  In Brave and Heymann (1993) a simplified version of statecharts called Hierarchical Finite State Machines (HFSMs) is considered for solving a class of control problems under full observation.  ...  Introduction The Fault Detection and Isolation (FDI) problem consists of identifying and exactly characterizing possible incipient faults arising in the operation of a dynamical system.  ... 
doi:10.1007/s10626-008-0044-5 fatcat:kuueke5bh5bdnm7rfbj7atpgc4

The dynamic hierarchical Dirichlet process

Lu Ren, David B. Dunson, Lawrence Carin
2008 Proceedings of the 25th international conference on Machine learning - ICML '08  
The dynamic hierarchical Dirichlet process (dHDP) is developed to model the timeevolving statistical properties of sequential data sets.  ...  Conclusions The proposed dynamic hierarchical Dirichlet process (dHDP) extends the HDP (Teh et al., 2005) , imposing a dynamic time dependence so that the initial mixture model and the subsequent time-dependent  ...  However, in many real applications, such as seasonal market analysis and gene investigation for disease, data are mea-Appearing in Proceedings of the 25 th International Conference on Machine Learning  ... 
doi:10.1145/1390156.1390260 dblp:conf/icml/RenDC08 fatcat:fgwl54niazcw7nkcdavaylpc4e

Unsupervised Video Summarization via Dynamic Modeling-Based Hierarchical Clustering

Karim M. Mahmoud, Nagia M. Ghanem, Mohamed A. Ismail
2013 2013 12th International Conference on Machine Learning and Applications  
This method utilizes a modified dynamic modelingbased hierarchical clustering algorithm that depends on the temporal order and sequential nature of the video to fasten the clustering process.  ...  Second, the modified dynamic modelingbased hierarchical clustering algorithm is applied (Step 2). Then, in step 3, one frame per cluster is selected as a key frame.  ...  Unlike other clustering algorithms, Chameleon [3] is an agglomerative hierarchical clustering that uses a dynamic modeling framework which overcomes the limitations of the other clustering algorithms  ... 
doi:10.1109/icmla.2013.140 dblp:conf/icmla/MahmoudGI13 fatcat:cxjtn3jpbvfv5i45g5amfrnvlq

Regularization of non-homogeneous dynamic Bayesian networks with global information-coupling based on hierarchical Bayesian models

Marco Grzegorczyk, Dirk Husmeier
2013 Machine Learning  
To relax the homogeneity assumption of classical dynamic Bayesian networks (DBNs), various recent studies have combined DBNs with multiple changepoint processes.  ...  Our hierarchical Bayesian model structure is similar to the one proposed in Punskaya et al. (2002) .  ...  Application to dynamic Bayesian networks Fixed changepoints We now generalize this coupling scheme for the interaction parameter prior distributions to non-homogeneous dynamic Bayesian networks (NH-DBNs  ... 
doi:10.1007/s10994-012-5326-3 fatcat:b2haxsjqcbfv5iosd3ov7kaeuu

A Hierarchical Model of Dynamics for Tracking People witha Single Video Camera

I Karaulova, P Hall, A Marshall
2000 Procedings of the British Machine Vision Conference 2000  
We propose a novel hierarchical model of human dynamics for view independent tracking of the human body in monocular video sequences. The model is trained using real data from a collection of people.  ...  Kinematics are encoded using Hierarchical Principal Component Analysis, and dynamics are encoded using Hidden Markov Models. The top of the hierarchy contains information about the whole body.  ...  Hierarchical Model of Human Dynamics A natural and common way to represent the human body is with connected parts.  ... 
doi:10.5244/c.14.36 dblp:conf/bmvc/KaraulovaHM00 fatcat:c4dqppqenzg6fh6stdgcgmogh4

Dynamic hierarchical Markov random fields and their application to web data extraction

Jun Zhu, Zaiqing Nie, Bo Zhang, Ji-Rong Wen
2007 Proceedings of the 24th international conference on Machine learning - ICML '07  
In this paper, we propose Dynamic Hierarchical Markov Random Fields (DHMRFs) to incorporate structural uncertainty in a discriminative manner.  ...  Hierarchical models have been extensively studied in various domains. However, existing models assume fixed model structures or incorporate structural uncertainty generatively.  ...  Dynamic Hierarchical Markov Random Fields In this section, we present the detailed description of Dynamic Hierarchical Markov Random Fields.  ... 
doi:10.1145/1273496.1273644 dblp:conf/icml/ZhuNZW07 fatcat:hgdcvpczc5dv3konp2nia7vycq

Clustering Dynamic Textures with the Hierarchical EM Algorithm for Modeling Video

A. Mumtaz, E. Coviello, G. R. G. Lanckriet, A. B. Chan
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
(BoS) codebooks for dynamic texture recognition.  ...  Dynamic texture (DT) is a probabilistic generative model, defined over space and time, that represents a video as the output of a linear dynamical system (LDS).  ...  Besides clustering dynamic textures, the HEM algorithm can be used to efficiently learn a DT mixture from large datasets of video, using a hierarchical estimation procedure.  ... 
doi:10.1109/tpami.2012.236 pmid:23681990 fatcat:xri7nmvfkvbcdav6md55xoitcm

A Time Optimal Parallel Algorithm for the Dynamic Programming on the Hierarchical Memory Machine

Koji Nakano
2014 2014 Second International Symposium on Computing and Networking  
The Hierarchical Memory Machine (HMM) is a theoretical parallel computing model that captures the essence of architecture of CUDA-enabled GPUs.  ...  Hence, this parallel algorithm achieves the acceleration rate of more than Û although the dynamic programming algorithm involves complicated stride memory access.  ...  Section II introduces three memory machines, the Discrete Memory Machine (DMM), the Unified Memory Machine (UMM), and the Hierarchical Memory Machine (HMM), which are theoretical parallel computing models  ... 
doi:10.1109/candar.2014.14 dblp:conf/ic-nc/Nakano14 fatcat:r7oym23oz5drnjmtxfqebzrz7i

Software Reliability Analysis Based on Hierarchical Dynamic Models and Bayesian Estimations using Machine Learning

Toru Kaise
2020 Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications  
In the Bayesian analysis, hierarchical prior models are structured with the Boltzmann machine, and empirical and expert knowledge priors are supposed.  ...  A Bayesian dynamic method for analysis of software debugging process data is handled. It is addressed to predict states of software reliability.  ...  The Weibull distribution is used for the hierarchical dynamical models, and the gamma distributions are used for the scale and shape parameters with the Boltzmann machine.  ... 
doi:10.5687/sss.2020.23 fatcat:qtctnf3vsjcn7au2wrdiv4ntg4

Building artificial memory to autonomous agents using dynamic and hierarchical finite state machine

T.F. Evers, S.R. Musse
Proceedings of Computer Animation 2002 (CA 2002)  
We use dynamic and hierarchical finite state machine (DHFSM) in order to represent the agents past experiences.  ...  This paper presents an approach to build artificial memory of autonomous agents using dynamic and hierarchical Finite State Machine (DHFSM).  ...  Kearney et al [6] proposed a Hierarchical Concurrent State Machine (HSCM), this approach uses multiple, concurrent state machines. More focused on urban context, Donikian et al.  ... 
doi:10.1109/ca.2002.1017527 dblp:conf/ca/EversM02 fatcat:rdcr2uzfgfcqlpnso3honko56u

Propagative Deployment of Hierarchical Components in a Dynamic Network [chapter]

Didier Hoareau, Yves Mahéo
2005 Lecture Notes in Computer Science  
This paper addresses the distribution and the deployment of hierarchical components on heterogeneous dynamic networks.  ...  We propose a propagative, hierarchically-controlled deployment process for such networks and an ADL extension allowing the specification of this context-aware deployment.  ...  Distributed Hierarchical Component Model for Dynamic Networks In order to support network disconnections we propose a distributed hierarchical component model which allows an application to run in a degraded  ... 
doi:10.1007/11590712_9 fatcat:cel2grhflzhcfjwgom64yypnxi

Constraint-Based Deployment of Distributed Components in a Dynamic Network [chapter]

Didier Hoareau, Yves Mahéo
2006 Lecture Notes in Computer Science  
This paper addresses the distribution and the deployment of hierarchical components on heterogeneous dynamic networks.  ...  The deployment of hierarchical components is described: we present an ADL extension for specifying a context-aware deployment and we detail a hierarchicallycontrolled deployment designed for dynamic networks  ...  Using a hierarchical component-based approach for building an application that targets a dynamic network seems an attractive solution.  ... 
doi:10.1007/11682127_32 fatcat:jm52rdifwfgvhg2gugwatr6nbi

Hierarchical Evaluation of Environmental Impacts from Manufacturing System and Machine Perspective

Tim Heinemann, Philipp Schraml, Sebastian Thiede, Christian Eisele, Christoph Herrmann, Eberhard Abele
2014 Procedia CIRP  
This paper presents a hierarchical approach and a case study for a synergetic combination of tools for simulating machine behavior and manufacturing line performance as well as for the calculation of Total  ...  Methods and tools for evaluating energy efficiency of machines and manufacturing lines have become available recently.  ...  , dynamic system behavior and logistic linkage of system elements.  ... 
doi:10.1016/j.procir.2014.06.063 fatcat:2aejx53dpbg4jc73xufp6g4vje
« Previous Showing results 1 — 15 out of 192,512 results