The two-sample hypothesis testing problem is studied for the challenging scenario of high dimensional data sets with small sample sizes. We show that the two-sample hypothesis testing problem can be posed as a one-class set classification problem. In the set classification problem the goal is to classify a set of data points that are assumed to have a common class. We prove that the average probability of error given a set is less than or equal to the Bayes error and decreases as a power of $n$ number of sample data points in the set. We use the positive definite Set Kernel for directly mapping sets of data to an associated Reproducing Kernel Hilbert Space, without the need to learn a probability distribution. We specifically solve the two-sample hypothesis testing problem using a one-class SVM in conjunction with the proposed Set Kernel. We compare the proposed method with the Maximum Mean Discrepancy, F-Test and T-Test methods on a number of challenging simulated high dimensional and small sample size data. We also perform two-sample hypothesis testing experiments on six cancer gene expression data sets and achieve zero type-I and type-II error results on all data sets.

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning disentangled representations that encode distinct aspects of the data into separate variables. We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder. This allows us to train partially-specified models that make relatively strong assumptions about a subset of interpretable variables and rely on the flexibility of neural networks to learn representations for the remaining variables. We further define a general objective for semi-supervised learning in this model class, which can be approximated using an importance sampling procedure. We evaluate our framework's ability to learn disentangled representations, both by qualitative exploration of its generative capacity, and quantitative evaluation of its discriminative ability on a variety of models and datasets.

Discovering a correlation from one variable to another variable is of fundamental scientific and practical interest. While existing correlation measures are suitable for discovering average correlation, they fail to discover hidden or potential correlations. To bridge this gap, (i) we postulate a set of natural axioms that we expect a measure of potential correlation to satisfy; (ii) we show that the rate of information bottleneck, i.e., the hypercontractivity coefficient, satisfies all the proposed axioms; (iii) we provide a novel estimator to estimate the hypercontractivity coefficient from samples; and (iv) we provide numerical experiments demonstrating that this proposed estimator discovers potential correlations among various indicators of WHO datasets, is robust in discovering gene interactions from gene expression time series data, and is statistically more powerful than the estimators for other correlation measures in binary hypothesis testing of canonical examples of potential correlations.

The MPs behind this independent review certainly seem to think so. Culture Secretary Karen Bradley suggested AI has "the potential to improve our everyday lives", while Business Secretary Greg Clark praised the "huge social and economic benefits its use can bring". More than that: they want to make Britain the world leader in AI and add £630bn to the UK economy. With UK productivity having remained largely stagnant since the 2008 financial crisis, we need to start innovating in areas like AI to create bold new ways of working. But to make this work we need more than government reports.

The many potential social and economic benefits from advances in AI-based technologies depend entirely on the environment in which these technologies evolve, says the Royal Society. According to a new report from the UK's science academy, urgent consideration needs to be given to the "careful stewardship" needed over the next ten years to ensure that the dividends from machine learning – the form of artificial intelligence that allows machines to learn from data – benefit all in UK society. Machine Learning: the power and promise of computers that learn by example, published today (25 April 2017), comes at a critical time in the rapid development and use of this technology, and the growing debate about how it will reshape the UK economy and people's lives. Crucially the report calls for research funding bodies to support a new wave of machine learning research that goes beyond technical challenges, and into areas aimed at addressing public confidence in machine learning – vital to the UK maintaining its internationally competitive edge at the forefront of this area. The report also offers the first evidence about the UK public's views on machine learning, including the application areas about which they are particularly positive, and the need for the real-world data feeding the growth of this technology to be dealt with fairly and securely.

At this year's Notting Hill Carnival, the Metropolitan Police used facial recognition technology for the first time. Paul Wiles, the biometrics commissioner, reported that it was a test to see how the technology performed in such a bustling scenario. In theory, police records of 20 million faces can be cross-referenced with other crime data to identify likely offenders. In fact, we are seeing an explosion in new tech across the public sphere. Until now the model has been somewhat conservative, digitising processes humans once did.

"Ugh," my dad used to grunt when I switched on Radio 1 . "This music sounds like it was written by a computer". It's a criticism that's been levelled at synthpop for years. But what if it was true? Taryn Southern, a YouTube star and content creator, has just released a song she wrote with the help of artificial intelligence.

Last week, Caitlin Jenner and a robot called Sophia talked about what it means to be human and a woman. Yet, while the 60,000-strong audience they addressed at a tech-friendly Web Summit in Lisbon appeared cutting edge, their industry is in danger of inheriting elements of the old industries they consider part of a dinosaur age. Sexism and homophobia in Hollywood, the media and politics has been exposed by recent scandals. It is normally newspapers that are compared to the extinct monsters of the past by Silicon Valley types. One hundred and 98 local newspapers have closed in Britain alone in little over a decade.

Rhegmatogenous retinal detachment (RRD) is a highly curable condition if properly treated early1, 2; however, if it is left untreated and develops proliferative changes, it becomes an uncontrollable condition called proliferative vitreoretinopathy (PVR). PVR is a serious condition that can result in blindness regardless of repeated treatments3,4,5. It is important, therefore, for patients to be seen and treated at a vitreoretinal centre at the early RRD stage to preserve visual function. However, establishing such vitreoretinal centres that provide advanced ophthalmological procedures is not practical because of rising social security costs, a problem that is troubling many nations around the world6. On the other hand, medical equipment has made remarkable advances, and one such advancement is the ultra–wide-field scanning laser ophthalmoscope (Optos 200Tx; Optos PLC, Dunfermline, United Kingdom).

They are outdated, and the cause of 20 incidents a day in the UK. Architectural firm Umbrellium reckons it's got a solution: a sensor-packed digital crossing that responds to your movements. "We've been designing a pedestrian crossing for the 21st century," says Usman Haque, Umbrellium's founding partner. "Crossings that you know were designed in the 1950s, when there was a different type of city and interaction." This smart crossing doesn't just look more modern than the 60 years old versions; it uses machine learning to make the crossings safer.