Based in San Francisco, Marina Krakovsky is the author of The Middleman Economy: How Brokers, Agents, Dealers, and Everyday Matchmakers Create Value and Profit (Palgrave Macmillan, 2015). Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and full citation on the first page.

Last year, the United States Customs and Border Protection rolled out a recognition pilot program that uses biometric recognition tools like face and iris scanners. The program will snag "imposters" using a fake passport at airports, and what's more, reduce wait times at security checkpoints. But what might identify individuals even more conclusively and speed travelers on their way more swiftly is another kind of biometrics, based on the ear. Scientists have taken note that the curves of the cartilage, the protrusions of the auricle, and the hollow of the concha cava are all, like fingerprints, features distinctive to each person. The way noise bounces within their folds allows the ears to guarantee a highly accurate identification of who we are, Steve Beeby, professor of Electronic Systems and Devices at University of Southampton, told the Telegraph back in 2009.

For many years I lived in Eugene, Oregon, also known as "track-town USA" for its long tradition in track and field. Each summer high-profile meets like the United States National Championships or Olympic Trials would bring world-class competitors to the University of Oregon's Hayward Field. It was exciting to bump into great athletes at the local cafe or ice cream shop, or even find myself lifting weights or running on a track next to them. One morning I was shocked to be passed as if standing still by a woman running 400-meter repeats. Her training pace was as fast as I could run a flat out sprint over a much shorter distance.

Alex Honnold has his own verb. "To honnold"--usually written as "honnolding"--is to stand in some high, precarious place with your back to the wall, looking straight into the abyss. The verb was inspired by photographs of Honnold in precisely that position on Thank God Ledge, located 1,800 feet off the deck in Yosemite National Park. Honnold side-shuffled across this narrow sill of stone, heels to the wall, toes touching the void, when, in 2008, he became the first rock climber ever to scale the sheer granite face of Half Dome alone and without a rope. Had he lost his balance, he would have fallen for 10 long seconds to his death on the ground far below. Honnold is history's greatest ever climber in the free solo style, meaning he ascends without a rope or protective equipment of any kind. Above about 50 feet, any fall would likely be lethal, which means that, on epic days of soloing, he might spend 12 or more hours in the Death Zone. On the hardest parts of some climbing routes, his fingers will have no more contact with the rock than most people have with the touchscreens of their phones, while his toes press down on edges as thin as sticks of gum. Just watching a video of Honnold climbing will trigger some degree of vertigo, heart palpitations, or nausea in most people, and that's if they can watch them at all. Even Honnold has said that his palms sweat when he watches himself on film. All of this has made Honnold the most famous climber in the world.

The invention of religion is a big bang in human history. Gods and spirits helped explain the unexplainable, and religious belief gave meaning and purpose to people struggling to survive. But what if everything we thought we knew about religion was wrong? What if belief in the supernatural is window dressing on what really matters--elaborate rituals that foster group cohesion, creating personal bonds that people are willing to die for. Anthropologist Harvey Whitehouse thinks too much talk about religion is based on loose conjecture and simplistic explanations. Whitehouse directs the Institute of Cognitive and Evolutionary Anthropology at Oxford University. For years he's been collaborating with scholars around the world to build a massive body of data that grounds the study of religion in science. Whitehouse draws on an array of disciplines--archeology, ethnography, history, evolutionary psychology, cognitive science--to construct a profile of religious practices. Whitehouse's fascination with religion goes back to his own groundbreaking field study of traditional beliefs in Papua New Guinea in the 1980s.

Following the seminal idea of Tukey, data depth is a function that measures how close an arbitrary point of the space is located to an implicitly defined center of a data cloud. Having undergone theoretical and computational developments, it is now employed in numerous applications with classification being the most popular one. The R-package ddalpha is a software directed to fuse experience of the applicant with recent achievements in the area of data depth and depth-based classification. ddalpha provides an implementation for exact and approximate computation of most reasonable and widely applied notions of data depth. These can be further used in the depth-based multivariate and functional classifiers implemented in the package, where the $DD\alpha$-procedure is in the main focus. The package is expandable with user-defined custom depth methods and separators. The implemented functions for depth visualization and the built-in benchmark procedures may also serve to provide insights into the geometry of the data and the quality of pattern recognition.

We consider the problem of estimating the mean and covariance of a distribution from iid samples in $\mathbb{R}^n$, in the presence of an $\eta$ fraction of malicious noise; this is in contrast to much recent work where the noise itself is assumed to be from a distribution of known type. The agnostic problem includes many interesting special cases, e.g., learning the parameters of a single Gaussian (or finding the best-fit Gaussian) when $\eta$ fraction of data is adversarially corrupted, agnostically learning a mixture of Gaussians, agnostic ICA, etc. We present polynomial-time algorithms to estimate the mean and covariance with error guarantees in terms of information-theoretic lower bounds. As a corollary, we also obtain an agnostic algorithm for Singular Value Decomposition.

Many modern statistical applications ask for the estimation of a covariance (or precision) matrix in settings where the number of variables is larger than the number of observations. There exists a broad class of ridge-type estimators that employs regularization to cope with the subsequent singularity of the sample covariance matrix. These estimators depend on a penalty parameter and choosing its value can be hard, in terms of being computationally unfeasible or tenable only for a restricted set of ridge-type estimators. Here we introduce a simple graphical tool, the spectral condition number plot, for informed heuristic penalty parameter selection. The proposed tool is computationally friendly and can be employed for the full class of ridge-type covariance (precision) estimators.

In cardiac magnetic resonance imaging, fully-automatic segmentation of the heart enables precise structural and functional measurements to be taken, e.g. from short-axis MR images of the left-ventricle. In this work we propose a recurrent fully-convolutional network (RFCN) that learns image representations from the full stack of 2D slices and has the ability to leverage inter-slice spatial dependences through internal memory units. RFCN combines anatomical detection and segmentation into a single architecture that is trained end-to-end thus significantly reducing computational time, simplifying the segmentation pipeline, and potentially enabling real-time applications. We report on an investigation of RFCN using two datasets, including the publicly available MICCAI 2009 Challenge dataset. Comparisons have been carried out between fully convolutional networks and deep restricted Boltzmann machines, including a recurrent version that leverages inter-slice spatial correlation. Our studies suggest that RFCN produces state-of-the-art results and can substantially improve the delineation of contours near the apex of the heart.

Classification is the task of predicting the class labels of objects based on the observation of their features. In contrast, quantification has been defined as the task of determining the prevalences of the different sorts of class labels in a target dataset. The simplest approach to quantification is Classify & Count where a classifier is optimised for classification on a training set and applied to the target dataset for the prediction of class labels. In the case of binary quantification, the number of predicted positive labels is then used as an estimate of the prevalence of the positive class in the target dataset. Since the performance of Classify & Count for quantification is known to be inferior its results typically are subject to adjustments. However, some researchers recently have suggested that Classify & Count might actually work without adjustments if it is based on a classifer that was specifically trained for quantification. We discuss the theoretical foundation for this claim and explore its potential and limitations with a numerical example based on the binormal model with equal variances. In order to identify an optimal quantifier in the binormal setting, we introduce the concept of local Bayes optimality. As a side remark, we present a complete proof of a theorem by Ye et al. (2012).