9,123 research outputs found
Maximum Likelihood Estimation for the Offset-Normal Shape Distributions Using EM
No full textThe offset-normal shape distribution is defined as the induced shape distribution of a Gaussian distributed random configuration in the plane. Such distributions were introduced by Dryden and Mardia (1991) and represent an important parameterized family of shape distributions for shape analysis. This article reports a method for performing maximum likelihood estimation of parameters involved. The method consists of an EM algorithm with simple update rules and is shown to be easily applicable in many practical examples. We also show the necessary adjustments needed for using this algorithm for shape regression, missing landmark data, and mixtures of offset-normal shape distributions
Enseñanza de la escritura de Max Aub: comprensión y memoria
No full textEste texto analiza a obra testimonial de Max Aub sobre su experiencia en los campos de concentración en Francia desde una perspectiva de discursos comparados. Para destacar las estrategias de la escritura del autor recuperables por otros proyectos discursivos que persigan la sensibilización y la denuncia a través del cruce entre la comunicación y la éticaThis text analyses the testimonial work of Max Aub about his experience in the French concentration camps in France from comparative discourses approach. It emphasizes the writing strategies used by the author useful for other awareness and denounce discourses through the dialogue among communication and ethic
Learning in Markov Random Fields with Contrastive Free Energies
No full textLearning Markov random field (MRF) models is notoriously hard due to the presence of a global normalization factor. In this paper we present a new framework for learning MRF models based on the contrastive free energy (CF) objective function. In this scheme the parameters are updated in an attempt to match the average statistics of the data distribution and a distribution which is (partially or approximately) "relaxed" to the equilibrium distribution. We show that maximum likelihood, mean field, contrastive divergence and pseudo-likelihood objectives can be understood in this paradigm. Moreover, we propose and study a new learning algorithm: the "kstep Kikuchi/Bethe approximation". This algorithm is then tested on a conditional random field model with "skip-chain" edges to model long range interactions in text data. It is demonstrated that with no loss in accuracy, the training time is brought down on average from 19 hours (BP based learning) to 83 minutes, an order of magnitude improvement
Max Brooks literary reading flier
No full text2012 Bismarck State College Visiting Writers Series and ArtsQuest present: Max Brooks. April 25, 7:30 p.m.; Belle Mehus Auditorium. Max Brooks is the author of World War Z: An Oral History of the Zombie War and the graphic novel The Zombie Survival Guide: Recorded Attacks
Recommended from our members
Stochastic Gradient MCMC: Algorithms and Applications
No full textDespite the powerful advantages of Bayesian inference such as quantifying uncertainty, ac- curate averaged prediction, and preventing overfitting, the traditional Markov chain Monte Carlo (MCMC) method has been regarded unsuitable for large-scale problems because it required processing the entire dataset per iteration rather than using a small random mini- batch as performed in the stochastic gradient optimization. The first attempt toward the scalable MCMC method based on stochastic gradients is the stochastic gradient Langevin dynamics (SGLD) proposed by Welling and Teh [2011]. Originated from the Langevin Monte Carlo method, SGLD achieved O(n) computation per iteration (here, n is the size of a minibatch) by using stochastic gradients estimated using minibatches and skipping the Metropolis-Hastings accept-reject test.In this thesis, we introduce recent advances in the stochastic gradient MCMC method since the advent of SGLD. Our contributions are two-fold: algorithms and applications. In the algorithm part, we first propose the stochastic gradient Fisher scoring algorithm (SGFS) which resolves two drawbacks of SGLD: the poor mixing rate and the arbitrarily large bias occurred when using large step sizes. Then, we also propose the distributed SGLD (D-SGLD) algorithm which makes it possible to extend the power of stochastic gradient MCMC to the distributed computing systems. In the second part, we apply the developed SG-MCMC algorithms to the most popular large-scale problems: the topic modeling using the latent Dirichlet allocation model, recommender systems using matrix factorization, and community modeling in social networks using mixed membership stochastic blockmodels. By resolving the unique challenges raised by each of the applications, which make it difficult to directly use the existing SG-MCMC methods, we obtain the-state-of-the-art results outperforming existing approaches using collapsed Gibbs sampling, stochastic variational inference, or dis- tributed stochastic gradient descent
Differential Equations and Continuous-Time Deep Learning (Dagstuhl Seminar 22332)
No full textThis report documents the program and the outcomes of Dagstuhl Seminar 22332 "Differential Equations and Continuous-Time Deep Learning". Neural ordinary-differential equations and similar continuous model architectures have gained interest in recent years, due to the existence of a vast literature in calculus and numerical analysis. Thus, continuous models might lead to architectures with finer control over prior assumptions or theoretical understanding. In this seminar, we have sought to bring together researchers from traditionally disjoint areas - machine learning, numerical analysis, dynamical systems and their "consumers" - to try and develop a joint language about this novel modeling paradigm. Through talks & group discussions, we have identified common interests and we hope that this first seminar is but the first step on a joint journey
Max Frisch's novel: Stiller. A study
No full text The attempt is made in the following study to present an interpretation of the novel "Stiller" by the Swiss author, Max Frisch, by tracing through the novel the dominant themes of the graven-image or 'Bildnis' and that of the problem of freedom with reference to the novel's main character. ThesisMaster of Arts (MA
A Transfer Report on the Development of a Framework to Evaluate Search Interfaces for their Support of Different User Types and Search Tactics
No full textAs the understanding of search systems, user needs and seeking strategies is developing, the design of search user interfaces is evolving to support more complicated and exploratory forms of search. With the design of new search features that enable these richer modes of exploration, comes the need to better understand the support they provide. In this report a new evaluation framework is presented that analyses search features for how they a) contribute to an overall interface, b) allow users to carry out different search tactics, and c) support different types of users and their needs. The novel contributions of the framework improve on some of the limitations of typical user studies, and allow search systems to be systematically analysed in much more detail and in much less time. The presented evaluation framework is then validated in three ways. First the validity of the models used as the building blocks of the framework are investigated through related work. Second the method of integrating these building-block models is validated and strengthened by consensus of expert opinion. Third, the overall approach is validated by comparing its analyses to the results of previously carried out user studies. The validation process has shown both the value of the framework and identified areas of future work that should be addressed for the framework to be completed. This report concludes with the set of contributions that the framework makes, and why the remaining work will be challenging, but critical to the final design
Recent Advancements in Tractable Probabilistic Inference (Dagstuhl Seminar 22161)
No full textIn several real-world scenarios, decision making involves advanced reasoning under uncertainty, i.e. the ability to answer probabilistic queries. Typically, it is necessary to compute these answers in a limited amount of time. Moreover, in many domains, such as healthcare and economical decision making, it is crucial that the result of these queries is reliable, i.e. either exact or comes with approximation guarantees. In all these scenarios, tractable probabilistic inference and learning are becoming increasingly important.
Research on representations and learning algorithms for tractable inference embraces very different fields, each one contributing its own perspective. These include automated reasoning, probabilistic modeling, statistical and Bayesian inference and deep learning.
Among the many recent emerging venues in these fields there are: tractable neural density estimators such as autoregressive models and normalizing flows; deep tractable probabilistic circuits such as sum-product networks and sentential decision diagrams; approximate inference routines with guarantees on the quality of the approximation.
Each of these model classes occupies a particular spot in the continuum between tractability and expressiveness. That is, different model classes might offer appealing advantages in terms of efficiency or representation capabilities while trading-off other of these aspects.
So far, clear connections and a deeper understanding of the key differences among them have been hindered by the different languages and perspectives adopted by the different "souls" that comprise the tractable probabilistic modeling community.
This Dagstuhl Seminar brought together experts from these sub-communities and provided the perfect venue to exchange perspectives, deeply discuss the recent advancements and build strong bridges that can greatly propel interdisciplinary research
The subzero microbiome: Microbial activity in frozen and thawing soils
No full textMost of the Earth's biosphere is characterized by low temperatures (<5 °C) and cold-adapted microorganisms are widespread. These psychrophiles have evolved a complex range of adaptations of all cellular constituents to counteract the potentially deleterious effects of low kinetic energy environments and the freezing of water. Microbial life continues into the subzero temperature range, and this activity contributes to carbon and nitrogen flux in and out of ecosystems, ultimately affecting global processes. Microbial responses to climate warming and in particular, thawing of frozen soils are not yet well understood although the threat of microbial contribution to positive feedback of carbon flux is substantial. To date, several studies have examined microbial community dynamics in frozen soils and permafrost due to changing environmental conditions, and some have undertaken the complicated task of characterizing microbial functional groups and how their activity changes with changing conditions, either in situ or by isolating and characterizing macromolecules. With increasing temperature and wetter conditions microbial activity of key microbes and subsequent efflux of greenhouse gases also increase. In this review, we aim to provide an overview of microbial activity in seasonally frozen soils and permafrost. With a more detailed understanding of the microbiological activities in these vulnerable soil ecosystems, we can begin to predict and model future expectations for carbon release and climate change.Peer reviewe
- …
