Regionalization is the task of dividing up a landscape into homogeneous patches with similar properties. Although this task has a wide range of applications, it has two notable challenges. First, it is assumed that the resulting regions are both homogeneous and spatially contiguous. Second, it is well-recognized that landscapes are hierarchical such that fine-scale regions are nested wholly within broader-scale regions. To address these two challenges, first, we develop a spatially constrained spectral clustering framework for region delineation that incorporates the tradeoff between region homogeneity and spatial contiguity. The framework uses a flexible, truncated exponential kernel to represent the spatial contiguity constraints, which is integrated with the landscape feature similarity matrix for region delineation. To address the second challenge, we extend the framework to create fine-scale regions that are nested within broader-scaled regions using a greedy, recursive bisection approach. We present a case study of a terrestrial ecology data set in the United States that compares the proposed framework with several baseline methods for regionalization. Experimental results suggest that the proposed framework for regionalization outperforms the baseline methods, especially in terms of balancing region contiguity and homogeneity, as well as creating regions of more similar size, which is often a desired trait of regions.

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers without getting stuck in local critical points, and that such minimizers are often satisfactory at avoiding overfitting. How these two features can be kept under control in nonlinear devices composed of millions of tunable connections is a profound and far reaching open question. In this paper we study basic non-convex neural network models which learn random patterns, and derive a number of basic geometrical and algorithmic features which suggest some answers. We first show that the error loss function presents few extremely wide flat minima (WFM) which coexist with narrower minima and critical points. We then show that the minimizers of the cross-entropy loss function overlap with the WFM of the error loss. We also show examples of learning devices for which WFM do not exist. From the algorithmic perspective we derive entropy driven greedy and message passing algorithms which focus their search on wide flat regions of minimizers. In the case of SGD and cross-entropy loss, we show that a slow reduction of the norm of the weights along the learning process also leads to WFM. We corroborate the results by a numerical study of the correlations between the volumes of the minimizers, their Hessian and their generalization performance on real data.

The increasing accessibility of data provides substantial opportunities for understanding user behaviors. Unearthing anomalies in user behaviors is of particular importance as it helps signal harmful incidents such as network intrusions, terrorist activities, and financial frauds. Many visual analytics methods have been proposed to help understand user behavior-related data in various application domains. In this work, we survey the state of art in visual analytics of anomalous user behaviors and classify them into four categories including social interaction, travel, network communication, and transaction. We further examine the research works in each category in terms of data types, anomaly detection techniques, and visualization techniques, and interaction methods. Finally, we discuss the findings and potential research directions.

A recent hardware test of NASA's robotic assistant, 'Astrobees,' takes a new wave of space-bound autonomous helpers one step closer to reality. According to NASA, this month astronaut Anne McClain ran a hardware test of the robot, named'Bumble,' one of three robotic assistants launched to the International Space Station (ISS) on April 15. Scientists hope Bumble will carry out an array of housekeeping tasks like monitoring equipment and keeping inventory of supplies that NASA hopes will free up its astronauts to perform other more critical tasks relating to with their missions and experiments. Astrobees are just one of many robotic applications from NASA who is also studying the use of'soft' robotics that replace traditional hardware with malleable plastics'Astrobee will prove out robotic capabilities that will enable and enhance human exploration,' said Maria Bualat, Astrobee project manager at NASA's Ames Research Center in a statement. 'Performing such experiments in zero gravity will ultimately help develop new hardware and software for future space missions.'

Facebook isn't often thought of as a robotics company, but new work being done in the social media giant's skunkworks AI lab is trying to prove otherwise. The company on Monday gave a detailed look into some of the projects being undertaken by its AI researchers at its Menlo Park, California-based headquarters, many of which are aimed at making robots smarter. Among the machines being developed are walking hexapods that resemble a spider, a robotic arm and a human-like hand complete with sensors to help it touch. Facebook has a dedicated team of AI researchers at its headquarters in Menlo Park, California that are tasked with testing out robots. The hope is that their learnings can be applied to other AI software in the company and make those systems smarter.

Whether helping businesses grow through divestitures and carve outs, or optimizing diligence for corporate board members and C-Suite decision makers, AI and ML in M&A are here to stay. We always read about new technology disrupting the status quo through innovation and AI, but how is this changing Mergers and Acquisitions? I was pleased to take a deep dive this month in Dallas -- discussing what's new since last year's The Deal conference in Chicago -- with my Grant Thornton colleagues Jim Peko, National Managing Principal of Transaction Services, and Jason Pizza, Managing Director of Strategic Solutions. Technology is nothing new in the complex world of M&A. For years, conventional technologies like Excel spreadsheets were central to analysts' M&A work.

Of all cancers worldwide, lung cancer is the deadliest. It takes more than 1.7 million lives per year -- more than breast, prostate and colorectal cancer combined. Part of the problem is that the majority of cancers aren't caught until later stages, when interventions tend to be less successful. Google is determined to change that, and with its new AI-based tool, it hopes to make lung cancer prediction more accurate and more accessible. To screen for lung cancer, radiologists typically view hundreds of images from a single CT scan.

"It began three and a half billion years ago in a pool of muck, when a molecule made a copy of itself and so became the ultimate ancestor of all earthly life. It began four million years ago, when brain volumes began climbing rapidly in the hominid line. In less than thirty years, it will end." Jaan Tallinn stumbled across these words in 2007, in an online essay called "Staring into the Singularity." The "it" is human civilization.

Deep Learning is really starting to establish itself as a major new tool in visual effects. Currently the tools are still in their infancy but they are changing the way visual effects can be approached. Instead of a pipeline consisting of modelling, texturing, lighting and rendering, these new approaches are hallucinating or plausibly creating imagery that is based on training data sets. Machine Learning, the superset of Deep Learning and similar approaches have had great success in image classification, image recognition and image synthesis. At fxguide we covered Synthesia in the UK, a company born out of research first published as Face2Face.

Israeli radiology startup Aidoc has received FDA clearance for its AI-based product meant to help identify potential cases of pulmonary embolism in chest CT scans. Pulmonary embolism (PE) – which occurs when a blood clot gets lodged in the lung – is considered a silent killer that causes up to 200,000 deaths a year in the United States. The condition often strikes with little to no warning and diagnosis of a case can be extremely time-sensitive. Aidoc's technology doesn't require dedicated hardware and runs continuously on hospital systems, automatically ingesting radiological images. The 70-person company focuses on workflow optimization in radiology to help triage high risk patients for additional and faster review.