Université de Montréal

About: Université de Montréal is a education organization based out in Montreal, Quebec, Canada. It is known for research contribution in the topics: Population & Poison control. The organization has 45641 authors who have published 100476 publications receiving 4004007 citations. The organization is also known as: University of Montreal & UdeM.

Learning structured embeddings of knowledge bases

Abstract: Many Knowledge Bases (KBs) are now readily available and encompass colossal quantities of information thanks to either a long-term funding effort (e.g. WordNet, OpenCyc) or a collaborative process (e.g. Freebase, DBpedia). However, each of them is based on a different rigid symbolic framework which makes it hard to use their data in other systems. It is unfortunate because such rich structured knowledge might lead to a huge leap forward in many other areas of AI like natural language processing (word-sense disambiguation, natural language understanding, ...), vision (scene classification, image semantic annotation, ...) or collaborative filtering. In this paper, we present a learning process based on an innovative neural network architecture designed to embed any of these symbolic representations into a more flexible continuous vector space in which the original knowledge is kept and enhanced. These learnt embeddings would allow data from any KB to be easily used in recent machine learning methods for prediction and information retrieval. We illustrate our method on WordNet and Freebase and also present a way to adapt it to knowledge extraction from raw text.

Density estimation using Real NVP

Abstract: Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation and latent variable manipulations.

Incidence, risk factors and consequences of ICU delirium.

Abstract: Delirium in the critically ill is reported in 11–80% of patients. We estimated the incidence of delirium using a validated scale in a large cohort of ICU patients and determined the associated risk factors and outcomes. Prospective study in a 16-bed medical-surgical intensive care unit (ICU). 820 consecutive patients admitted to ICU for more than 24 h. Tools used were: the Intensive Care Delirium Screening Checklist for delirium, Richmond Agitation and Sedation Scale for sedation, and Numerical Rating Scale for pain. Risk factors were evaluated with univariate and multivariate analysis, and factors influencing mortality were determined using Cox regression. Delirium occurred in 31.8% of 764 patients. Risk of delirium was independently associated with a history of hypertension (OR 1.88, 95% CI 1.3–2.6), alcoholism (2.03, 1.2–3.2), and severity of illness (1.25, 1.03–1.07 per 5-point increment in APACHE II score) but not with age or corticosteroid use. Sedatives and analgesics increased the risk of delirium when used to induce coma (OR 3.2, 95% CI 1.5–6.8), and not otherwise. Delirium was linked to longer ICU stay (11.5 ± 11.5 vs. 4.4 ± 3.9 days), longer hospital stay (18.2 ± 15.7 vs. 13.2 ± 19.4 days), higher ICU mortality (19.7% vs. 10.3%), and higher hospital mortality (26.7% vs. 21.4%). Delirium is associated with a history of hypertension and alcoholism, higher APACHE II score, and with clinical effects of sedative and analgesic drugs.

Comparison of candesartan, enalapril, and their combination in congestive heart failure: randomized evaluation of strategies for left ventricular dysfunction (RESOLVD) pilot study. The RESOLVD Pilot Study Investigators.

Abstract: Background—We investigated the effects of candesartan (an angiotensin II antagonist) alone, enalapril alone, and their combination on exercise tolerance, ventricular function, quality of life (QOL)...