A classic approach for learning Bayesian networks from data is to identify a maximum a posteriori (MAP) network structure. In the case of discrete Bayesian networks, MAP networks are selected by maximising one of several possible Bayesian Dirichlet (BD) scores; the most famous is the Bayesian Dirichlet equivalent uniform (BDeu) score from Heckerman et al (1995). The key properties of BDeu arise from its uniform prior over the parameters of each local distribution in the network, which makes structure learning computationally efficient; it does not require the elicitation of prior knowledge from experts; and it satisfies score equivalence. In this paper we will review the derivation and the properties of BD scores, and of BDeu in particular, and we will link them to the corresponding entropy estimates to study them from an information theoretic perspective. To this end, we will work in the context of the foundational work of Giffin and Caticha (2007), who showed that Bayesian inference can be framed as a particular case of the maximum relative entropy principle. We will use this connection to show that BDeu should not be used for structure learning from sparse data, since it violates the maximum relative entropy principle; and that it is also problematic from a more classic Bayesian model selection perspective, because it produces Bayes factors that are sensitive to the value of its only hyperparameter. Using a large simulation study, we found in our previous work (Scutari, 2016) that the Bayesian Dirichlet sparse (BDs) score seems to provide better accuracy in structure learning; in this paper we further show that BDs does not suffer from the issues above, and we recommend to use it for sparse data instead of BDeu. Finally, will show that these issues are in fact different aspects of the same problem and a consequence of the distributional assumptions of the prior.

What is machine learning / ai? How to lean machine learning in practice? There are a lot of interested people out there but many do not know where to start. The difficult question basically is how to start actually learning it? Especially beginners might get discouraged because of statistics and math which is an integral part of machine learning.

O'Reilly Media and NumFOCUS will present Jupyter Pop-up Boston on March 21 at District Hall, in Boston's Seaport neighborhood. The event is a day-long exploration of Project Jupyter in a casual setting, focused on the local community. We'll have a dozen talks, a panel discussion, an "Ask Me Anything" with experts on the project, plus lots of time to meet and talk with people who share common interests and concerns. The timing is quite interesting for Jupyter. Success stories from 2016-17 such as the data science program at UC Berkeley illustrate the power of JupyterHub deployments at scale, in both education and industry.

Now, you at least have an idea of what machine learning is and how useful for businesses and the IT industry in general it is. So, it is high time to learn how to implement these magic algorithms. It is worth noting that there are already several ready-made machine learning tools intended to somehow simplify the work for your developers. Google launched its machine learning service called Awareness API last year. This service allows developers to understand the context in which customers use their smartphones.

Will you have a job next week? Will your skill set be valued in the job market in the years to come? If not, do you know what you need to do to keep your skills up-to-date? Over the past few decades, we have witnessed a large number of innovations that have changed how we live and work. I have been working as a social media consultant for over a decade, a job that was not even dreamed of when I graduated college.

We are not only living in an age where women are being under-represented in many spheres of economic life, but technology could make this even worse. Women hold just 19% of board directorships in the US and Europe. This gender gap in the boardroom persists, despite the fact that, on average, women have obtained higher educational qualifications than their male counterparts for more than two decades in many OECD countries. And the main reason is social bias. This is on the verge of being further reinforced by artificial intelligence, as current data being used to train machines to learn are often biased.

Estimating the structure of directed acyclic graphs (DAGs, also known as Bayesian networks) is a challenging problem since the search space of DAGs is combinatorial and scales superexponentially with the number of nodes. Existing approaches rely on various local heuristics for enforcing the acyclicity constraint and are not well-suited to general purpose optimization packages for their solution. In this paper, we introduce a fundamentally different strategy: We formulate the structure learning problem as a smooth, constrained optimization problem over real matrices that avoids this combinatorial constraint entirely. This is achieved by a novel characterization of acyclicity that is not only smooth but also exact. The resulting nonconvex, constrained program involves smooth functions whose gradients are easy to compute and only involve elementary matrix operations. By using existing black-box optimization routines, our method uses global search to find an optimal DAG and can be implemented in about 50 lines of Python and outperforms existing methods without imposing any structural constraints.

To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes. The generative network of WHAI has a hierarchy of gamma distributions, while the inference network of WHAI is a Weibull upward-downward variational autoencoder, which integrates a deterministic-upward deep neural network, and a stochastic-downward deep generative model based on a hierarchy of Weibull distributions. The Weibull distribution can be used to well approximate a gamma distribution with an analytic Kullback-Leibler divergence, and has a simple reparameterization via the uniform noise, which help efficiently compute the gradients of the evidence lower bound with respect to the parameters of the inference network. The effectiveness and efficiency of WHAI are illustrated with experiments on big corpora.

NEW YORK, NY – Duff & Phelps, the premiere global valuation and corporate finance advisor, has selected eBrevia's award-winning artificial intelligence technology to deploy throughout the enterprise for faster contract review. Duff & Phelps has already been using the software for large-scale contract review projects to augment its professionals' expertise and bring increased value to clients more quickly. The firm will continue to leverage the software for a variety of use cases as it advises clients on a range of strategic and complex business challenges. Duff & Phelps has been increasing its presence in the contract management space from two perspectives: legal management consulting and post-acquisition integration. As a legal management consultant, Duff & Phelps advises clients on selection and implementation of contract lifecycle management systems.

Trouble is brewing among the students of the Girls Domestic Science School, a well-known private institution at Hitotsubashi, Kanda, which enjoys a good reputation in educational circles and has contributed greatly to the advancement of female education, the courses including sewing, embroidery and foreign-style cooking. The school recently received a monetary donation amounting to ¥13,000 from Mr. Kamesaburo Yamashita, the well-known "narikin" of Kobe, who has amassed a big fortune though the sale of steamers. Several days ago the girls school referred to had a visit from an aged lady, who was alleged to have been sent by Mr. Yamashita, the patron of the school, on the mission of selecting a prospective bride for the son or nephew of the narikin. The old lady was treated by the school faculty with marked respect, and as though she came with the object of inspection, the true purpose of her visit being hidden as far as possible. Madame Haruko Hatoyama, the widow of the late Dr. Hatoyama, ex-minister of justice and dean of Waseda who is the superintendent of the teaching staff of the school, ordered the class to stop the lesson and gave the visitor the privilege of leisurely examining the personal beauty of the girl students of the graduating class of a certain course.