Four members of our research team spent the past week at the Conference on Empirical Methods in Natural Language Processing (EMNLP 2017) in Copenhagen, Denmark. The conference handbook can be found here and the proceedings can be found here. The program consisted of two days of workshops and tutorials and three days of main conference. Videos of the conference talks and presentations can be found here.The conference was superbly organized, had a great venue, and a social event with fireworks. With 225 long papers, 107 papers, and 9 TACL papers accepted, there was a clear uptick of submissions compared to last year.

We consider the problem of nonparametric regression under shape constraints. The main examples include isotonic regression (with respect to any partial order), unimodal/convex regression, additive shape-restricted regression, and constrained single index model. We review some of the theoretical properties of the least squares estimator (LSE) in these problems, emphasizing on the adaptive nature of the LSE. In particular, we study the risk behavior of the LSE, and its pointwise limiting distribution theory, with special emphasis to isotonic regression. We survey various methods for constructing pointwise confidence intervals around these shape-restricted functions. We also briefly discuss the computation of the LSE and indicate some open research problems and future directions.

At Qure, we regularly work on segmentation and object detection problems and we were therefore interested in reviewing the current state of the art. In this post, I review the literature on semantic segmentation. Although the results are not directly applicable to medical images, I review these papers because research on the natural images is much more mature than that of medical images. Post is organized as follows: I first explain the semantic segmentation problem, give an overview of the approaches and summarize a few interesting papers. In a later post, I'll explain why medical images are different from natural images and examine how the approaches from this review fare on a dataset representative of medical images.

Researchers at the University of Chicago have successfully trained a neural network to generate realistic Yelp reviews. With online reviews acting as a lifeblood for restaurants, replication of this technology could harm restaurant owners. Moreover, this technology has the potential to be easily replicated and harmful to other industries, including ecommerce and news. "Let me Yelp it" are familiar words to any hungry restaurant-goer quickly looking for a reliable spot to dine at. Online reviews, both in terms of volume and rating, are one of the most important factors used by diners when determining where to eat.

So, you want to become a data scientist or may be you are already one and want to expand your tool repository. You have landed at the right place. The aim of this page is to provide a comprehensive learning path to people new to python for data analysis. This path provides a comprehensive overview of steps you need to learn to use Python for data analysis. If you already have some background, or don't need all the components, feel free to adapt your own paths and let us know how you made changes in the path.

The random dot product graph (RDPG) is an independent-edge random graph that is analytically tractable and, simultaneously, either encompasses or can successfully approximate a wide range of random graphs, from relatively simple stochastic block models to complex latent position graphs. In this survey paper, we describe a comprehensive paradigm for statistical inference on random dot product graphs, a paradigm centered on spectral embeddings of adjacency and Laplacian matrices. We examine the analogues, in graph inference, of several canonical tenets of classical Euclidean inference: in particular, we summarize a body of existing results on the consistency and asymptotic normality of the adjacency and Laplacian spectral embeddings, and the role these spectral embeddings can play in the construction of single- and multi-sample hypothesis tests for graph data. We investigate several real-world applications, including community detection and classification in large social networks and the determination of functional and biologically relevant network properties from an exploratory data analysis of the Drosophila connectome. We outline requisite background and current open problems in spectral graph inference.

We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds---e.g. the characteristic silverlining and the "whiteness" of the inner body---challenging for methods based solely on Monte Carlo integration or diffusion theory. We approach the problem differently. Instead of simulating all light transport during rendering, we pre-learn the spatial and directional distribution of radiant flux from tens of cloud exemplars. To render a new scene, we sample visible points of the cloud and, for each, extract a hierarchical 3D descriptor of the cloud geometry with respect to the shading location and the light source. The descriptor is input to a deep neural network that predicts the radiance function for each shading configuration. We make the key observation that progressively feeding the hierarchical descriptor into the network enhances the network's ability to learn faster and predict with high accuracy while using few coefficients. We also employ a block design with residual connections to further improve performance. A GPU implementation of our method synthesizes images of clouds that are nearly indistinguishable from the reference solution within seconds interactively. Our method thus represents a viable solution for applications such as cloud design and, thanks to its temporal stability, also for high-quality production of animated content.

Outliers are extreme values that deviate from other observations on data, they may indicate a variability in a measurement, experimental errors or a novelty. In other words, an outlier is an observation that diverges from an overall pattern on a sample. Outliers can be of two kinds: univariate and multivariate. Univariate outliers can be found when looking at a distribution of values in a single feature space. Multivariate outliers can be found in a n-dimensional space (of n-features).

Summary: With only slight tongue in cheek about the road ahead we report on the just passed House of Representative's new "Federal Automated Vehicle Policy" as well as similar policy just emerging in Germany. As a model of regulation on emerging AI technology we think they got this just about right. Just today (9/6/17) the US House of Representatives released its 116 page "Federal Automated Vehicles Policy". This still has to be reconciled and approved by the Senate but word is that shouldn't take long. Equally as interesting is that just two weeks ago the German federal government published its guidelines for Highly Automated Vehicles (HAV being the new name of choice for these vehicles).

Answer Set Programming (ASP) is a well-known paradigm of declarative programming with roots in logic programming and non-monotonic reasoning. Similar to other closely related problem-solving technologies, such as SAT/SMT, QBF, Planning and Scheduling, advancements in ASP solving are assessed in competition events. In this paper, we report about the design and results of the Sixth ASP Competition, which was jointly organized by the University of Calabria (Italy), Aalto University (Finland), and the University of Genoa (Italy), in affiliation with the 13th International Conference on Logic Programming and Non-Monotonic Reasoning. This edition maintained some of the design decisions introduced in 2014, e.g., the conception of sub-tracks, the scoring scheme, and the adherence to a fixed modeling language in order to push the adoption of the ASP-Core-2 standard. On the other hand, it featured also some novelties, like a benchmark selection stage classifying instances according to their empirical hardness, and a "Marathon" track where the top-performing systems are given more time for solving hard benchmarks.