Author: Alireza Bakhtiari KoohsorkhiPublisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Analysis of the Dirichlet Process Mixture Model with Application to Dialogue Act Classification
Author: Alireza Bakhtiari KoohsorkhiPublisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Applying Dirichlet Process Mixture Models to Compositional Data, with Application to Train Waybill Data
Author: Marie G. GantzConjugate Dirichlet Process Mixture Models
Author: David Boyack DahlDirichlet Process Mixture Modeling
Author: Yuting QiPublisher:
ISBN:
Category : Mixture distributions (Probability theory)
Languages : en
Pages : 258
Book Description
In this dissertation, we develop two novel statistical models utilizing the Dirichlet process (DP) prior: (i) a DP-based hidden Markov mixture model, and (ii) multi-task compressive sensing.
A Study on Variational Component Splitting Approach for Mixture Models
Author: Kamal Maanicshah Mathin HenryPublisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
Increase in use of mobile devices and the introduction of cloud-based services have resulted in the generation of enormous amount of data every day. This calls for the need to group these data appropriately into proper categories. Various clustering techniques have been introduced over the years to learn the patterns in data that might better facilitate the classification process. Finite mixture model is one of the crucial methods used for this task. The basic idea of mixture models is to fit the data at hand to an appropriate distribution. The design of mixture models hence involves finding the appropriate parameters of the distribution and estimating the number of clusters in the data. We use a variational component splitting framework to do this which could simultaneously learn the parameters of the model and estimate the number of components in the model. The variational algorithm helps to overcome the computational complexity of purely Bayesian approaches and the over fitting problems experienced with Maximum Likelihood approaches guaranteeing convergence. The choice of distribution remains the core concern of mixture models in recent research. The efficiency of Dirichlet family of distributions for this purpose has been proved in latest studies especially for non-Gaussian data. This led us to study the impact of variational component splitting approach on mixture models based on several distributions. Hence, our contribution is the application of variational component splitting approach to design finite mixture models based on inverted Dirichlet, generalized inverted Dirichlet and inverted Beta-Liouville distributions. In addition, we also incorporate a simultaneous feature selection approach for generalized inverted Dirichlet mixture model along with component splitting as another experimental contribution. We evaluate the performance of our models with various real-life applications such as object, scene, texture, speech and video categorization.
Extensions of Dirichlet Process Mixture Models
Author: Natalie BurnsPublisher:
ISBN:
Category :
Languages : en
Pages : 0
Book Description
bottom level to ensure that the random partitions of subjects within each GWG trajectory class rely sufficiently on the neonatal outcomes and are not dominated by the maternal characteristics. The second extension, the EDP-HDP, is a model which combines the advantages of the EDP with characteristics of the hierarchical Dirichlet process (HDP). In this model, we place a DP prior on the base measure in the bottom level of the EDP. We include the GWG trajectories in the bottom level of clustering and child cardiometabolic outcomes in the top level of clustering to predict the child outcomes using the GWG measurements. Incorporating the HDP in the bottom level of the EDP allows the GWG trajectory classes to be shared across outcome clusters.
Variational Approaches For Learning Finite Scaled Dirichlet Mixture Models
Author: Hieu Nguyen DinhPublisher:
ISBN:
Category :
Languages : en
Pages :
Book Description
With a massive amount of data created on a daily basis, the ubiquitous demand for data analysis is undisputed. Recent development of technology has made machine learning techniques applicable to various problems. Particularly, we emphasize on cluster analysis, an important aspect of data analysis. Recent works with excellent results on the aforementioned task using finite mixture models have motivated us to further explore their extents with different applications. In other words, the main idea of mixture model is that the observations are generated from a mixture of components, in each of which the probability distribution should provide strong flexibility in order to fit numerous types of data. Indeed, the Dirichlet family of distributions has been known to achieve better clustering performances than those of Gaussian when the data are clearly non-Gaussian, especially proportional data. Thus, we introduce several variational approaches for finite Scaled Dirichlet mixture models. The proposed algorithms guarantee reaching convergence while avoiding the computational complexity of conventional Bayesian inference. In summary, our contributions are threefold. First, we propose a variational Bayesian learning framework for finite Scaled Dirichlet mixture models, in which the parameters and complexity of the models are naturally estimated through the process of minimizing the Kullback-Leibler (KL) divergence between the approximated posterior distribution and the true one. Secondly, we integrate component splitting into the first model, a local model selection scheme, which gradually splits the components based on their mixing weights to obtain the optimal number of components. Finally, an online variational inference framework for finite Scaled Dirichlet mixture models is developed by employing a stochastic approximation method in order to improve the scalability of finite mixture models for handling large scale data in real time. The effectiveness of our models is validated with real-life challenging problems including object, texture, and scene categorization, text-based and image-based spam email detection.
The Application of Hidden Markov Models in Speech Recognition
Author: Mark GalesPublisher: Now Publishers Inc
ISBN: 1601981201
Category : Automatic speech recognition
Languages : en
Pages : 125
Book Description
The Application of Hidden Markov Models in Speech Recognition presents the core architecture of a HMM-based LVCSR system and proceeds to describe the various refinements which are needed to achieve state-of-the-art performance.
Text Analytics with Python
Author: Dipanjan SarkarPublisher: Apress
ISBN: 1484223888
Category : Computers
Languages : en
Pages : 397
Book Description
Derive useful insights from your data using Python. You will learn both basic and advanced concepts, including text and language syntax, structure, and semantics. You will focus on algorithms and techniques, such as text classification, clustering, topic modeling, and text summarization. Text Analytics with Python teaches you the techniques related to natural language processing and text analytics, and you will gain the skills to know which technique is best suited to solve a particular problem. You will look at each technique and algorithm with both a bird's eye view to understand how it can be used as well as with a microscopic view to understand the mathematical concepts and to implement them to solve your own problems. What You Will Learn: Understand the major concepts and techniques of natural language processing (NLP) and text analytics, including syntax and structure Build a text classification system to categorize news articles, analyze app or game reviews using topic modeling and text summarization, and cluster popular movie synopses and analyze the sentiment of movie reviews Implement Python and popular open source libraries in NLP and text analytics, such as the natural language toolkit (nltk), gensim, scikit-learn, spaCy and Pattern Who This Book Is For : IT professionals, analysts, developers, linguistic experts, data scientists, and anyone with a keen interest in linguistics, analytics, and generating insights from textual data
Reliability and Risk
Author: Nozer D. SingpurwallaPublisher: John Wiley & Sons
ISBN: 0470060336
Category : Mathematics
Languages : en
Pages : 396
Book Description
We all like to know how reliable and how risky certain situations are, and our increasing reliance on technology has led to the need for more precise assessments than ever before. Such precision has resulted in efforts both to sharpen the notions of risk and reliability, and to quantify them. Quantification is required for normative decision-making, especially decisions pertaining to our safety and wellbeing. Increasingly in recent years Bayesian methods have become key to such quantifications. Reliability and Risk provides a comprehensive overview of the mathematical and statistical aspects of risk and reliability analysis, from a Bayesian perspective. This book sets out to change the way in which we think about reliability and survival analysis by casting them in the broader context of decision-making. This is achieved by: Providing a broad coverage of the diverse aspects of reliability, including: multivariate failure models, dynamic reliability, event history analysis, non-parametric Bayes, competing risks, co-operative and competing systems, and signature analysis. Covering the essentials of Bayesian statistics and exchangeability, enabling readers who are unfamiliar with Bayesian inference to benefit from the book. Introducing the notion of “composite reliability”, or the collective reliability of a population of items. Discussing the relationship between notions of reliability and survival analysis and econometrics and financial risk. Reliability and Risk can most profitably be used by practitioners and research workers in reliability and survivability as a source of information, reference, and open problems. It can also form the basis of a graduate level course in reliability and risk analysis for students in statistics, biostatistics, engineering (industrial, nuclear, systems), operations research, and other mathematically oriented scientists, wherein the instructor could supplement the material with examples and problems.