MIT has developed a new machine learning model mean to predict the rate and pattern of spread of the COVID-19 novel coronavirus. The machine learning model was based on established epidemiological equations about outbreaks combined with publicly available data as well as neural network-based inference. When it was applied to the coronavirus spread data from late January to early March, its predictions proved accurate based on what actually happened leading up to April 1 in various regions worldwide. It also suggested that any relaxation or elimination of quarantine regulations in the immediate or near-term would result in an "exponential explosion" of infection rates. MIT researchers developed this calculation based only on the data collected about COVID-19's spread. Other prior calculations have incorporated data from other outbreaks such as SARS and MERS.

A commercial artificial intelligence (AI) system matched the accuracy of over 28,000 interpretations of breast cancer screening mammograms by 101 radiologists. Although the most accurate mammographers outperformed the AI system, it achieved a higher performance than the majority of radiologists (JNCI: J. Natl. With the addition of deep-learning convolutional neural networks, new AI systems for breast cancer screening improve upon the computer-aided detection (CAD) systems that radiologists have used since the 1990s. The AI system evaluated in this study -- conducted by radiologists and medical physicists at Radboud University Medical Centre -- has a feature classifier and image analysis algorithms to detect soft-tissue lesions and calcifications, and generates a "cancer suspicion" ranking of 1 to 10. The researchers examined unrelated datasets of images from nine previous clinical studies.

Scientists have harnessed artificial intelligence to translate brain signals into speech, in a step toward brain implants that one day could let people with impaired abilities speak their minds, according to a new study. In findings published Wednesday in the journal Nature, a research team at the University of California, San Francisco, introduced an experimental brain decoder that combined direct recording of signals from the brains of research subjects with artificial intelligence, machine learning and a speech synthesizer.

BREVARD COUNTY • MELBOURNE, FLORIDA -- Faculty and students from Florida Tech's Center for Advanced Data Analytics and Systems are working with a team from the U.S. Air Force Air Combat Command/Intelligence Data/Tech Futures Division and the Air Force Research Lab/Multi-Domain Sensing Autonomy Division to bring artificial intelligence and machine learning to COVID-19 planning and resource management. The goal of the Florida Tech work, which began in early April and could continue at least through the summer, is to strengthen the understanding of the effects COVID-19 has on Air Force missions and operations. "Our collaboration with Florida Tech has been critical to changing the way we think about data and present it to our commanders," said John Matyjas, ACC Chief Scientist and lead for their COVID Data Analytics Team. The CADAS team of Carlos Otero, Adrian M. Peter and Anthony O. Smith, supported by students Xavier Merino, David Elliott, Steven Wyatt, Benjamin Luchterhand, Evan Martino, Christopher Bonomi and David Nieves-Acaron, has developed capabilities to rapidly gain situational awareness and support the seamless integration of data-driven artificial intelligence (AI)/machine learning models for forecasting. "This task provides invaluable experience to our students while helping in the critical mission to better understand and utilize COVID-19-related data that ultimately can help the Air Force manage and move beyond this challenging situation," Otero said.

People in England can return to work if they can't work from home Restrictions to curb the spread of coronavirus are being eased slightly in England this week, but many have criticised the government for creating confusion with a new slogan telling people to "stay alert", which replaces previous advice to "stay at home." In a video message broadcast on Sunday evening, prime minister Boris Johnson announced the following changes to the government's policy in England, which are listed in full online and will come into effect from Wednesday 13 May: These new policies mean that social distancing rules in England are now different from the advice given to UK citizens in Scotland, Wales and Northern Ireland. Scotland's first minister Nicola Sturgeon said people should continue to "stay at home", and Northern Ireland's first minister Arlene Foster also rejected the new slogan. Some London Underground platforms were packed with passengers this morning following last night's announcement.

In new plans that offer a national reimagining of how to fight wildfires amid the risk of the coronavirus spreading through crews, it's not clear how officials will get the testing and equipment needed to keep firefighters safe in what's expected to be a difficult fire season. A U.S. group instead put together broad guidelines to consider when sending crews to blazes, with agencies and firefighting groups in different parts of the country able to tailor them to fit their needs. The wildfire season has largely begun, and states in the American West that have suffered catastrophic blazes in recent years could see higher-than-normal levels of wildfire because of drought. "This plan is intended to provide a higher-level framework of considerations and not specific operational procedures," the National Multi-Agency Coordination Group, made up of representatives from federal agencies who worked with state and local officials, wrote in each of the regional plans. "It is not written in terms of'how to' but instead provides considerations of'what,' 'why,' and'where.'"

The goal of this work is to train a neural network which approximates solutions to the Navier-Stokes equations across a region of parameter space, in which the parameters define physical properties such as domain shape and boundary conditions. The contributions of this work are threefold: 1) To demonstrate that neural networks can be efficient aggregators of whole families of parameteric solutions to physical problems, trained using data created with traditional, trusted numerical methods such as finite elements. Advantages include extremely fast evaluation of pressure and velocity at any point in physical and parameter space (asymptotically, ~3 $\mu s$ / query), and data compression (the network requires 99\% less storage space compared to its own training data). 2) To demonstrate that the neural networks can accurately interpolate between finite element solutions in parameter space, allowing them to be instantly queried for pressure and velocity field solutions to problems for which traditional simulations have never been performed. 3) To introduce an active learning algorithm, so that during training, a finite element solver can automatically be queried to obtain additional training data in locations where the neural network's predictions are in most need of improvement, thus autonomously acquiring and efficiently distributing training data throughout parameter space. In addition to the obvious utility of Item 2, above, we demonstrate an application of the network in rapid parameter sweeping, very precisely predicting the degree of narrowing in a tube which would result in a 50\% increase in end-to-end pressure difference at a given flow rate. This capability could have applications in both medical diagnosis of arterial disease, and in computer-aided design.

We propose a simple yet effective multiple kernel clustering algorithm, termed simple multiple kernel k-means (SimpleMKKM). It extends the widely used supervised kernel alignment criterion to multi-kernel clustering. Our criterion is given by an intractable minimization-maximization problem in the kernel coefficient and clustering partition matrix. To optimize it, we re-formulate the problem as a smooth minimization one, which can be solved efficiently using a reduced gradient descent algorithm. We theoretically analyze the performance of SimpleMKKM in terms of its clustering generalization error. Comprehensive experiments on 11 benchmark datasets demonstrate that SimpleMKKM outperforms state of the art multi-kernel clustering alternatives.

In this paper, we investigate the use of deep learning for solving a classical NP-Hard single machine scheduling problem where the criterion is to minimize the total tardiness. Instead of designing an end-to-end machine learning model, we utilize well known decomposition of the problem and we enhance it with a data-driven approach. We have designed a regressor containing a deep neural network that learns and predicts the criterion of a given set of jobs. The network acts as a polynomial-time estimator of the criterion that is used in a single-pass scheduling algorithm based on Lawler's decomposition theorem. Essentially, the regressor guides the algorithm to select the best position for each job. The experimental results show that our data-driven approach can efficiently generalize information from the training phase to significantly larger instances (up to 350 jobs) where it achieves an optimality gap of about 0.5%, which is four times less than the gap of the state-of-the-art NBR heuristic.

Various structured argumentation frameworks utilize preferences as part of their standard inference procedure to enable reasoning with preferences. In this paper, we consider an inverse of the standard reasoning problem, seeking to identify what preferences over assumptions could lead to a given set of conclusions being drawn. We ground our work in the Assumption-Based Argumentation (ABA) framework, and present an algorithm which computes and enumerates all possible sets of preferences over the assumptions in the system from which a desired conflict free set of conclusions can be obtained under a given semantic. After describing our algorithm, we establish its soundness, completeness and complexity.