We point out an issue with Theorem 5 appearing in "Group-based active query selection for rapid diagnosis in time-critical situations". Theorem 5 bounds the expected number of queries for a greedy algorithm to identify the class of an item within a constant factor of optimal. The Theorem is based on correctness of a result on minimization of adaptive submodular functions. We present an example that shows that a critical step in Theorem A.11 of "Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization" is incorrect.

The main task in oil and gas exploration is to gain an understanding of the distribution and nature of rocks and fluids in the subsurface. Well logs are records of petro-physical data acquired along a borehole, providing direct information about what is in the subsurface. The data collected by logging wells can have significant economic consequences, due to the costs inherent to drilling wells, and the potential return of oil deposits. In this paper, we describe preliminary work aimed at building a general framework for well log prediction. First, we perform a descriptive and exploratory analysis of the gaps in the neutron porosity logs of more than a thousand wells in the North Sea. Then, we generate artificial gaps in the neutron logs that reflect the statistics collected before. Finally, we compare Artificial Neural Networks, Random Forests, and three algorithms of Linear Regression in the prediction of missing gaps on a well-by-well basis.

With the huge influx of various data nowadays, extracting knowledge from them has become an interesting but tedious task among data scientists, particularly when the data come in heterogeneous form and have missing information. Many data completion techniques had been introduced, especially in the advent of kernel methods. However, among the many data completion techniques available in the literature, studies about mutually completing several incomplete kernel matrices have not been given much attention yet. In this paper, we present a new method, called Mutual Kernel Matrix Completion (MKMC) algorithm, that tackles this problem of mutually inferring the missing entries of multiple kernel matrices by combining the notions of data fusion and kernel matrix completion, applied on biological data sets to be used for classification task. We first introduced an objective function that will be minimized by exploiting the EM algorithm, which in turn results to an estimate of the missing entries of the kernel matrices involved. The completed kernel matrices are then combined to produce a model matrix that can be used to further improve the obtained estimates. An interesting result of our study is that the E-step and the M-step are given in closed form, which makes our algorithm efficient in terms of time and memory. After completion, the (completed) kernel matrices are then used to train an SVM classifier to test how well the relationships among the entries are preserved. Our empirical results show that the proposed algorithm bested the traditional completion techniques in preserving the relationships among the data points, and in accurately recovering the missing kernel matrix entries. By far, MKMC offers a promising solution to the problem of mutual estimation of a number of relevant incomplete kernel matrices.

Police in Durham are preparing to go live with an artificial intelligence (AI) system designed to help officers decide whether or not a suspect should be kept in custody. The system classifies suspects at a low, medium or high risk of offending and has been trialled by the force. It has been trained on five years' of offending histories data. One expert said the tool could be useful, but the risk that it could skew decisions should be carefully assessed. Data for the Harm Assessment Risk Tool (Hart) was taken from Durham police records between 2008 and 2012.

The next time you go under the knife for retinal surgery, it may not be a human hand holding the blade. That's because a revolutionary surgical system developed University of Oxford in the United Kingdom, which just passed its first set of clinical trials, is able to perform these intricate operations better than even the steadiest surgeon. The problem lies in the pulse. Retinal surgeries rely on creating miniscule holes in the eye to gain access to the retina itself, a 10 micron thick flap of membrane that converts light into electrical signals that the brain can interpret. In the case of issues like an epiretinal membrane, essentially a scar on the retina caused by anything from injury to disease to just growing old, even the flow of blood through a surgeon's hands is enough to throw off their accuracy, raising the odds that they'll cut too deeply and make matters worse.

We're living in an aging nation where the older population is dramatically growing at an unprecedented rate. With aging comes the need to keep our memory sharp to maintain our quality of life. Researchers at Florida State University suggest trendy brain games for adults do little to improve memory, or stave off cognitive decline and disorders. "Our findings and previous studies confirm there's very little evidence these types of games can improve your life in a meaningful way," said Wally Boot, study author and associate professor of psychology at FSU, in a statement. Cognitive training, popularly known as "brain training," has been touted for its claims of improving cognitive abilities such as working memory, reasoning and processing speed. Brain-training companies like Lumosity, Cogmed, and Brain HQ promise to make us smarter, but Boot and his colleagues have found there is no solid scientific evidence to back up this promise.

Monday, May 8th, London, UK - The Chief Science Officer of the Biogerontology Research Foundation (BGRF) will present new research on artificial intelligence for drug discovery at the NVIDIA Graphics Technology Conference (GTC) at the San Jose Convention Center, on Wednesday, May 10, 1:00 PM - 1:50 PM alongside two AI scientists from the BGRF and Insilico Medicine, where they will deliver a presentation titled "Applications of Generative Adversarial Networks to Drug Discovery in Oncology and Infectious Diseases". NVIDIA is the leader in computational hardware optimized for deep learning-based applications, and they are on the forefront of supporting research companies and institutions applying deep learning to grand unsolved problems, with the application of deep learning to drug discovery and development being no exception, as they described in detail in their article "Creating New Drugs, Faster: How AI Promises to Speed Drug Development". "The application of deep learning to ageing research is poised to make rapid progress on many fronts in the years to come. Foremost among these are the application of deep learning to the characterization of quantifiable and practically-measurable biomarkers of ageing (a necessity for the eventual regulatory evaluation and approval of healthspan-extending therapies) and the acceleration of drug discovery and development timelines by using deep learning to characterize drug candidates according to likely efficacy and safety prior to preclinical and clinical trials. AI, machine learning and deep learning have disrupted many industries and areas of activity that were previously the exclusive arena of human cognition, and in the coming years it seems likely that the pharmaceutical industry and the process of drug discovery and development will come to be radically disrupted by AI and deep learning-based approaches as well" said Franco Cortese, Deputy Director & Trustee of the Biogerontology Research Foundation.

The March issue of Health Affairs demonstrates the potential of health care delivery system innovation to improve value for both patients and clinicians. Technology innovations such as machine learning and artificial intelligence systems are promising breakthroughs to improve diagnostic accuracy, tailor treatments, and even eventually replace work performed by clinicians, especially that of radiologists and pathologists. Machine-learning systems infer patterns, relationships, and rules directly from large volumes of data in ways that can far exceed human cognitive capacities. As the computational underpinning of tools such as e-mail spam filters, product and content recommendations, targeted advertisements, and, more recently, autonomous vehicles, machine learning is already ubiquitous in many economic sectors. Yet, machine-learning applications are still used sparingly today in the delivery of care.

Amir Moravej, an Iranian computer engineer in Montreal, quietly worked last year on building software to help people navigate the Canadian immigration system. He saw it as a way for others to avoid the same immigration travails he suffered a few years earlier. Then came the American presidential election. "Trump accelerated everything," said Mr. Moravej, 33, the chief executive of a software start-up named Botler AI. With immigration taking center stage in American politics and elsewhere, Botler AI began putting more resources into building a chatbot tailored to one of Canada's immigration programs.

Windows may dominate the worldwide desktop market, but Microsoft is working to adapt the operating system for all kinds of devices, from giant displays like the Surface Studio to mixed reality headsets like the HoloLens. The event comes after Microsoft recently debuted new products including Windows 10 S and the Surface Laptop . Harman Kardon also just revealed its new Invoke smart speaker, which is powered by Microsoft's Cortana virtual assistant. Terry Myerson, Microsoft's executive vice president of the Windows and devices group, sat down with TIME to discuss the future of Windows, Microsoft's hardware efforts, virtual reality, and more. Below is a transcript of our conversation edited for length and clarity.