Google's use of Brits' medical records to train an AI and treat people was legally "inappropriate," says Dame Fiona Caldicott, the National Data Guardian at the UK's Department of Health. In April 2016 it was revealed the web giant had signed a deal with the Royal Free Hospital in London to build an artificially intelligent application called Streams, which would analyze patients' records and identify those who had acute kidney damage. As part of the agreement, the hospital handed over 1.6 million sets of NHS medical files to DeepMind, Google's highly secretive machine-learning nerve center. However, not every patient was aware that their data was being given to Google to train the Streams AI model. And the software was supposed to be used only as a trial – an experiment with software-driven diagnosis – yet it was ultimately used to detect kidney injuries in people and alert clinicians that they needed treatment. Dame Caldicott has told the hospital's medical director Professor Stephen Powis that he overstepped the mark: it's one thing to create and test an application, it's another thing entirely to use in-development code to treat people.

work is creative, problem-solving work which requires high levels of education and is usually well-rewarded. Manual work is skilled dexterous physical work. It usually does not require high levels of education and is typically poorly-paid and highly-precarious (i.e.

As the drone industry continues to grow, aerial enthusiasts are flying -- and leaping -- to new heights. Latvia-based company Aerones completed "the world's first drone jump" last week with their 28-propeller drone. Skydiver Ingus Augstkalns, who came up with the daring idea, used the top of a 393-foot communications tower as a launch pad. Augstkalns clung to handlebars suspended from the bottom of the aircraft as he rose to over 1,000 feet before letting go and deploying his parachute. "Emotions are fantastic," Augstkalns said in a statement.

This humanoid robot is likeable in every way: he's fun, surprising, resourceful and, above all, brand new. In fact, he's the very first robot ever seen in a store in Europe! To pull off this amazing feat, the teams at Capgemini France worked closely with Aldebaran to design the appropriate software. "A robot has three possible roles: greeting, conversation and data analysis. Kiabi initially prioritized the first two, so we focused on those," explains Jean-Claude Guyard.

CORRECTS FROM HUTCHIS TO HUTCHINS -British IT expert Marcus Hutchins who has been branded a hero for slowing down the WannaCry global cyber attack, during an interview in Ilfracombe, England, Monday, May 15, 2017. Hutchins thwarted the virus that took computer files hostage around the world, including the British National Health computer network, telling The Associated Press he doesn't consider himself a hero but fights malware because "it's the right thing to do.''

Predictive business process monitoring methods exploit logs of completed cases of a process in order to make predictions about running cases thereof. Existing methods in this space are tailor-made for specific prediction tasks. Moreover, their relative accuracy is highly sensitive to the dataset at hand, thus requiring users to engage in trial-and-error and tuning when applying them in a specific setting. This paper investigates Long Short-Term Memory (LSTM) neural networks as an approach to build consistently accurate models for a wide range of predictive process monitoring tasks. First, we show that LSTMs outperform existing techniques to predict the next event of a running case and its timestamp. Next, we show how to use models for predicting the next task in order to predict the full continuation of a running case. Finally, we apply the same approach to predict the remaining time, and show that this approach outperforms existing tailor-made methods.

Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects -- typically neglected by conventional quantum chemistry approaches -- we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potentials of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the introduction of a fully automated sampling scheme and the use of molecular forces during neural network potential training. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n-alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all these case studies we find excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.

Building on a survey of previous theories of serendipity and creativity, we advance a sequential model of serendipitous occurrences. We distinguish between serendipity as a service and serendipity in the system itself, clarify the role of invention and discovery, and provide a measure for the serendipity potential of a system. While a system can arguably not be guaranteed to be serendipitous, it can have a high potential for serendipity. Practitioners can use these theoretical tools to evaluate a computational system's potential for unexpected behaviour that may have a beneficial outcome. In addition to a qualitative features of serendipity potential, the model also includes quantitative ratings that can guide development work. We show how the model is used in three case studies of existing and hypothetical systems, in the context of evolutionary computing, automated programming, and (next-generation) recommender systems. From this analysis, we extract recommendations for practitioners working with computational serendipity, and outline future directions for research.

A fundamental goal in network neuroscience is to understand how activity in one region drives activity elsewhere, a process referred to as effective connectivity. Here we propose to model this causal interaction using integro-differential equations and causal kernels that allow for a rich analysis of effective connectivity. The approach combines the tractability and flexibility of autoregressive modeling with the biophysical interpretability of dynamic causal modeling. The causal kernels are learned nonparametrically using Gaussian process regression, yielding an efficient framework for causal inference. We construct a novel class of causal covariance functions that enforce the desired properties of the causal kernels, an approach which we call GP CaKe. By construction, the model and its hyperparameters have biophysical meaning and are therefore easily interpretable. We demonstrate the efficacy of GP CaKe on a number of simulations and give an example of a realistic application on magnetoencephalography (MEG) data.

Bayesian optimization through Gaussian process regression is an effective method of optimizing an unknown function for which every measurement is expensive. It approximates the objective function and then recommends a new measurement point to try out. This recommendation is usually selected by optimizing a given acquisition function. After a sufficient number of measurements, a recommendation about the maximum is made. However, a key realization is that the maximum of a Gaussian process is not a deterministic point, but a random variable with a distribution of its own. This distribution cannot be calculated analytically. Our main contribution is an algorithm, inspired by sequential Monte Carlo samplers, that approximates this maximum distribution. Subsequently, by taking samples from this distribution, we enable Thompson sampling to be applied to (armed-bandit) optimization problems with a continuous input space. All this is done without requiring the optimization of a nonlinear acquisition function. Experiments have shown that the resulting optimization method has a competitive performance at keeping the cumulative regret limited.