The paper deals with learning probability distributions of observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian update for conjugate priors. We establish a connection between the gradient conjugate prior update and the maximization of the log-likelihood of the predictive distribution. Unlike for the Bayesian neural networks, we use deterministic weights of neural networks, but rather assume that the ground truth distribution is normal with unknown mean and variance and learn by the neural networks the parameters of a prior (normal-gamma distribution) for these unknown mean and variance. The update of the parameters is done, using the gradient that, at each step, directs towards minimizing the Kullback--Leibler divergence from the prior to the posterior distribution (both being normal-gamma). We obtain a corresponding dynamical system for the prior's parameters and analyze its properties. In particular, we study the limiting behavior of all the prior's parameters and show how it differs from the case of the classical full Bayesian update. The results are validated on synthetic and real world data sets.

Non-small-cell lung cancer (NSCLC) represents approximately 80-85% of lung cancer diagnoses and is the leading cause of cancer-related death worldwide. Recent studies indicate that image-based radiomics features from positron emission tomography-computed tomography (PET/CT) images have predictive power on NSCLC outcomes. To this end, easily calculated functional features such as the maximum and the mean of standard uptake value (SUV) and total lesion glycolysis (TLG) are most commonly used for NSCLC prognostication, but their prognostic value remains controversial. Meanwhile, convolutional neural networks (CNN) are rapidly emerging as a new premise for cancer image analysis, with significantly enhanced predictive power compared to other hand-crafted radiomics features. Here we show that CNN trained to perform the tumor segmentation task, with no other information than physician contours, identify a rich set of survival-related image features with remarkable prognostic value. In a retrospective study on 96 NSCLC patients before stereotactic-body radiotherapy (SBRT), we found that the CNN segmentation algorithm (U-Net) trained for tumor segmentation in PET/CT images, contained features having strong correlation with 2- and 5-year overall and disease-specific survivals. The U-net algorithm has not seen any other clinical information (e.g. survival, age, smoking history) than the images and the corresponding tumor contours provided by physicians. Furthermore, through visualization of the U-Net, we also found convincing evidence that the regions of progression appear to match with the regions where the U-Net features identified patterns that predicted higher likelihood of death. We anticipate our findings will be a starting point for more sophisticated non-intrusive patient specific cancer prognosis determination.

We present the first acoustic side-channel attack that recovers what users type on the virtual keyboard of their touch-screen smartphone or tablet. When a user taps the screen with a finger, the tap generates a sound wave that propagates on the screen surface and in the air. We found the device's microphone(s) can recover this wave and "hear" the finger's touch, and the wave's distortions are characteristic of the tap's location on the screen. Hence, by recording audio through the built-in microphone(s), a malicious app can infer text as the user enters it on their device. We evaluate the effectiveness of the attack with 45 participants in a real-world environment on an Android tablet and an Android smartphone. For the tablet, we recover 61% of 200 4-digit PIN-codes within 20 attempts, even if the model is not trained with the victim's data. For the smartphone, we recover 9 words of size 7--13 letters with 50 attempts in a common side-channel attack benchmark. Our results suggest that it not always sufficient to rely on isolation mechanisms such as TrustZone to protect user input. We propose and discuss hardware, operating-system and application-level mechanisms to block this attack more effectively. Mobile devices may need a richer capability model, a more user-friendly notification system for sensor usage and a more thorough evaluation of the information leaked by the underlying hardware.

Heart rate estimation from electrocardiogram signals is very important for the early detection of cardiovascular diseases. However, due to large individual differences and varying electrocardiogram signal quality, there does not exist a single reliable estimation algorithm that works well on all subjects. Every algorithm may break down on certain subjects, resulting in a significant estimation error. Ensemble regression, which aggregates the outputs of multiple base estimators for more reliable and stable estimates, can be used to remedy this problem. Moreover, active learning can be used to optimally select a few trials from a new subject to label, based on which a stacking ensemble regression model can be trained to aggregate the base estimators. This paper proposes four active stacking approaches, and demonstrates that they all significantly outperform three common unsupervised ensemble regression approaches, and a supervised stacking approach which randomly selects some trials to label. Remarkably, our active stacking approaches only need three or four labeled trials from each subject to achieve an average root mean squared estimation error below three beats per minute, making them very convenient for real-world applications. To our knowledge, this is the first research on active stacking, and its application to heart rate estimation.

Nintendo may be about to give the Switch a refresh. A new report from The Wall Street Journal claims that the company could be planning two new consoles for as soon as this summer. Citing anonymous people "familiar with the matter," the report says that Nintendo is prepping two new devices, a cheaper version of the Switch that would be the equivalent of a Nintendo 3DS replacement as well as a more powerful model, similar to how Microsoft and Sony have each released souped-up versions of their game consoles. The more enhanced Switch, however, won't be as powerful as the Xbox One X or PlayStation 4 Pro and Nintendo has a track record of looking to differentiate its latest products with more than just graphical boosts. Both devices could make appearances at June's E3 gaming event in Los Angeles, the Journal reports.

Technologies Inc. aims to release a mass-market flying motorcycle by 2022, Chief Executive Officer Shuhei Komatsu said. Technologies, which mainly develops small drones, hopes to sell the product, called a "hover bike," in emerging economies in Africa, the Middle East and Asia with poor road infrastructure. Many companies around the world are developing flying cars. Technologies is among those trying to enter the market. "We'll create a (flying) bike first, in order to get flying cars widely used in society eventually," Komatsu said.

Almost 1.5million jobs are at risk of being replaced by robots, a new survey by the Office of National Statistics (ONS) has revealed. Women and young people are at higher risk than other demographics in their jobs. A total of 7.4 per cent of all jobs are under threat, a figure which is slightly down from the 8.1 per cent number from 2011. Almost 1.5million jobs are at risk of being replaced by robots, a new survey by the Office of National Statistics (ONS) has revealed. The ONS analysed the jobs of 20 million people from 2011 and 2017 in England and found that that 7.4 per cents are at high risk of automation.

An online tool has been unveiled which is capable of bringing black and white photographs to life instantaneously by adding colour to them using artificial intelligence. Colourisation of old images is a normally time consuming process which requires specialist training and expensive software. The tool, ColouriseSG, is able to do it for free from only a single digital image and works on iconic historical photographs and old family portraits. Try it for yourself here or via the interactive tool below. The artificial intelligence is able to colourise images for free from only a single digital image and works on iconic historical photographs and old family portraits.

Apple appears to be broadcasting eerie footage from inside of its own headquarters, hours before one of its biggest events in years. Tim Cook and other senior Apple staff are set to take to the stage in Apple's own Steve Jobs Theater later today, announcing the company's new products. Unlike previous events, it will not be releasing hardware or software, but instead showing off new subscription services that allow people access to films, TV and news. That event is set to be livestreamed through Apple's own website. And that video appears to have already begun: with strange footage from inside the theatre itself.

Many rumours have been circulating for Apple's'Show Time' event on 25 March, chief among them a new TV service and a premium news subscription. But a new report now suggests there may also be a gaming subscription service, allowing people to pay one flat fee and get access to a variety of games on their iPhones and iPads. The service could rival Google's recently announced Stadia platform as well as being part of Apple's broader plan to make more money from streaming service subscriptions. We'll tell you what's true. You can form your own view.