WASHINGTON, DC (March 8, 2017)--Interventional radiologists at the University of California at Los Angeles (UCLA) are using technology found in self-driving cars to power a machine learning application that helps guide patients' interventional radiology care, according to research presented today at the Society of Interventional Radiology's 2017 Annual Scientific Meeting. The researchers used cutting-edge artificial intelligence to create a "chatbot" interventional radiologist that can automatically communicate with referring clinicians and quickly provide evidence-based answers to frequently asked questions. This allows the referring physician to provide real-time information to the patient about the next phase of treatment, or basic information about an interventional radiology treatment. "We theorized that artificial intelligence could be used in a low-cost, automated way in interventional radiology as a way to improve patient care," said Edward W. Lee, M.D., Ph.D., assistant professor of radiology at UCLA's David Geffen School of Medicine and one of the authors of the study. "Because artificial intelligence has already begun transforming many industries, it has great potential to also transform health care."

A major inference task in Bayesian networks is explaining why some variables are observed in their particular states using a set of target variables. Existing methods for solving this problem often generate explanations that are either too simple (underspecified) or too complex (overspecified). In this paper, we introduce a method called Most Relevant Explanation (MRE) which finds a partial instantiation of the target variables that maximizes the generalized Bayes factor (GBF) as the best explanation for the given evidence. Our study shows that GBF has several theoretical properties that enable MRE to automatically identify the most relevant target variables in forming its explanation. In particular, conditional Bayes factor (CBF), defined as the GBF of a new explanation conditioned on an existing explanation, provides a soft measure on the degree of relevance of the variables in the new explanation in explaining the evidence given the existing explanation. As a result, MRE is able to automatically prune less relevant variables from its explanation. We also show that CBF is able to capture well the explaining-away phenomenon that is often represented in Bayesian networks. Moreover, we define two dominance relations between the candidate solutions and use the relations to generalize MRE to find a set of top explanations that is both diverse and representative. Case studies on several benchmark diagnostic Bayesian networks show that MRE is often able to find explanatory hypotheses that are not only precise but also concise.

Sudyanti, Putu Ayu, Rao, Vinayak

This paper addresses challenges in flexibly modeling multimodal data that lie on constrained spaces. Applications include climate or crime measurements in a geographical area, or flow-cytometry experiments, where unsuitable recordings are discarded. A simple approach to modeling such data is through the use of mixture models, with each component following an appropriate truncated distribution. Problems arise when the truncation involves complicated constraints, leading to difficulties in specifying the component distributions, and in evaluating their normalization constants. Bayesian inference over the parameters of these models results in posterior distributions that are doubly-intractable. We address this problem via an algorithm based on rejection sampling and data augmentation. We view samples from a truncated distribution as outcomes of a rejection sampling scheme, where proposals are made from a simple mixture model, and are rejected if they violate the constraints. Our scheme proceeds by imputing the rejected samples given mixture parameters, and then resampling parameters given all samples. We study two modeling approaches: mixtures of truncated components and truncated mixtures of components. In both situations, we describe exact Markov chain Monte Carlo sampling algorithms, as well as approximations that bound the number of rejected samples, achieving computational efficiency and lower variance at the cost of asymptotic bias. Overall, our methodology only requires practitioners to provide an indicator function for the set of interest. We present results on simulated data and apply our algorithm to two problems, one involving flow-cytometry data, and the other, crime recorded in the city of Chicago.

Mehta, Pankaj, Bukov, Marin, Wang, Ching-Hao, Day, Alexandre G. R., Richardson, Clint, Fisher, Charles K., Schwab, David J.

Machine Learning (ML) is one of the most exciting and dynamic areas of modern research and application. The purpose of this review is to provide an introduction to the core concepts and tools of machine learning in a manner easily understood and intuitive to physicists. The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, and generalization before moving on to more advanced topics in both supervised and unsupervised learning. Topics covered in the review include ensemble models, deep learning and neural networks, clustering and data visualization, energy-based models (including MaxEnt models and Restricted Boltzmann Machines), and variational methods. Throughout, we emphasize the many natural connections between ML and statistical physics. A notable aspect of the review is the use of Python notebooks to introduce modern ML/statistical packages to readers using physics-inspired datasets (the Ising Model and Monte-Carlo simulations of supersymmetric decays of proton-proton collisions). We conclude with an extended outlook discussing possible uses of machine learning for furthering our understanding of the physical world as well as open problems in ML where physicists maybe able to contribute. (Notebooks are available at https://physics.bu.edu/~pankajm/MLnotebooks.html )