We consider log-supermodular models on binary variables, which are probabilistic models with negative log-densities which are submodular. These models provide probabilistic interpretations of common combinatorial optimization tasks such as image segmentation. In this paper, we focus primarily on parameter estimation in the models from known upper-bounds on the intractable log-partition function. We show that the bound based on separable optimization on the base polytope of the submodular function is always inferior to a bound based on "perturb-and-MAP" ideas. Then, to learn parameters, given that our approximation of the log-partition function is an expectation (over our own randomization), we use a stochastic subgradient technique to maximize a lower-bound on the log-likelihood. This can also be extended to conditional maximum likelihood. We illustrate our new results in a set of experiments in binary image denoising, where we highlight the flexibility of a probabilistic model to learn with missing data.

When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically puts more emphasis on exploration to provide more information to the models.

Our focus is on realistically modeling and forecasting dynamic networks of face-to-face contacts among individuals. Important aspects of such data that lead to problems with current methods include the tendency of the contacts to move between periods of slow and rapid changes, and the dynamic heterogeneity in the actors' connectivity behaviors. Motivated by this application, we develop a novel method for Locally Adaptive DYnamic (LADY) network inference. The proposed model relies on a dynamic latent space representation in which each actor's position evolves in time via stochastic differential equations. Using a state space representation for these stochastic processes and P\'olya-gamma data augmentation, we develop an efficient MCMC algorithm for posterior inference along with tractable procedures for online updating and forecasting of future networks. We evaluate performance in simulation studies, and consider an application to face-to-face contacts among individuals in a primary school.

Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular "graph convolutions", a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph---atoms, bonds, distances, etc.---which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

Top data science teams around the world are doing incredible work on some of the most interesting datasets in the world. Google has more data on human interests than every 20th century researcher, while Uber seamlessly coordinates the itinerary and pricing of more than 1 million trips every day. With machine learning, and artificial intelligence, top data science teams are changing the way we ingest and process data, and they are coming up with actionable insights that impact the lives of millions. What if there were common patterns between the interviews top data science teams were giving that would let you master the data science interview process? What if the specific differences between various teams and their interview practices could be enumerated so that interviewing with a top data science team were more akin to a science than an art?

Programmers are trying to teach machines to be less sexist by helping them separate words from stereotypes. While computers may be neutral, unconscious human biases can be reflected in machine learning algorithms to analyse language. Such biases have been shown to have an impact before, where basic programs sorting job applications could end up discriminating against applicants based on key words. But one team in the US is trying to break the bias. Computers may be neutral, but unconscious biases can be reflected in machine learning algorithms to analyse language.

The MegaFace dataset contains 1 million images representing more than 690,000 unique people. It is the first benchmark that tests facial recognition algorithms at a million scale.University of Washington In the last few years, several groups have announced that their facial recognition systems have achieved near-perfect accuracy rates, performing better than humans at picking the same face out of the crowd. But those tests were performed on a dataset with only 13,000 images -- fewer people than attend an average professional U.S. soccer game. What happens to their performance as those crowds grow to the size of a major U.S. city? University of Washington researchers answered that question with the MegaFace Challenge, the world's first competition aimed at evaluating and improving the performance of face recognition algorithms at the million person scale.

Technology is really a marvel. So often, as new technology comes out and allows us to do things that were thought impossible in the past, we hear the phrase "The future is now." Popular Science and XPRIZE are teaming up to explore and explain technologies like these in a video series called Future First. Episode two of Future First is titled "Artificial Intelligence: Your Tutor and Nurse." In it, we take a look at artificial intelligence and its potential applications for education, health, and more.

Nasa has announced that it has found evidence of flowing water on Mars. Scientists have long speculated that Recurring Slope Lineae -- or dark patches -- on Mars were made up of briny water but the new findings prove that those patches are caused by liquid water, which it has established by finding hydrated salts. Several hundred camped outside the London store in Covent Garden. The 6s will have new features like a vastly improved camera and a pressure-sensitive "3D Touch" display

Coding will join this list in time, however, where it differs wildly from the afore mentioned examples is it is unlikely to be lovingly preserved for future generations to admire, fiddle with or better still, reactivate. Its essence will not be reified for one specific reason – it can't be touched and humans value tactility. We touch immediately, both inside and outside the womb. Today, we find ourselves at a pivotal moment in our existence and about to experience an exponential period of rapid technological growth the likes of which is quite probably beyond our comprehension and at a base level, will have serious implications for coding. We rather arrogantly think that because we have a good grasp of our own technological advancement so far, we can somehow predict the mass cultural and behavioural shift about to happen as we question our own skills in the world.