In recent years, a variety of ML architectures and techniques have seen success in producing skillful medium range weather forecasts. In particular, Vision Transformer (ViT)-based models (e.g. Pangu-Weather, FuXi) have shown strong performance, working nearly "out-of-the-box" by treating weather data as a multi-channel image on a rectilinear grid. While a rectilinear grid is appropriate for 2D images, weather data is inherently spherical and thus heavily distorted at the poles on a rectilinear grid, leading to disproportionate compute being used to model data near the poles. Graph-based methods (e.g. GraphCast) do not suffer from this problem, as they map the longitude-latitude grid to a spherical mesh, but are generally more memory intensive and tend to need more compute resources for training and inference. While spatially homogeneous, the spherical mesh does not lend itself readily to be modeled by ViT-based models that implicitly rely on the rectilinear grid structure. We present HEAL-ViT, a novel architecture that uses ViT models on a spherical mesh, thus benefiting from both the spatial homogeneity enjoyed by graph-based models and efficient attention-based mechanisms exploited by transformers. HEAL-ViT produces weather forecasts that outperform the ECMWF IFS on key metrics, and demonstrate better bias accumulation and blurring than other ML weather prediction models. Further, the lowered compute footprint of HEAL-ViT makes it attractive for operational use as well, where other models in addition to a 6-hourly prediction model may be needed to produce the full set of operational forecasts required.

Patient-independent detection of epileptic activities based on visual spectral representation of continuous EEG (cEEG) has been widely used for diagnosing epilepsy. However, precise detection remains a considerable challenge due to subtle variabilities across subjects, channels and time points. Thus, capturing fine-grained, discriminative features of EEG patterns, which is associated with high-frequency textural information, is yet to be resolved. In this work, we propose Scattering Transformer (ScatterFormer), an invariant scattering transform-based hierarchical Transformer that specifically pays attention to subtle features. In particular, the disentangled frequency-aware attention (FAA) enables the Transformer to capture clinically informative high-frequency components, offering a novel clinical explainability based on visual encoding of multichannel EEG signals. Evaluations on two distinct tasks of epileptiform detection demonstrate the effectiveness our method. Our proposed model achieves median AUCROC and accuracy of 98.14%, 96.39% in patients with Rolandic epilepsy. On a neonatal seizure detection benchmark, it outperforms the state-of-the-art by 9% in terms of average AUCROC.

New dishwasher technology could soon save you money on water, electricity and detergent, a study reveals. Researchers have performed simulations of a dishwasher system that uses superheated steam instead of soap to clean dishes. Superheated steam is an extremely high-temperature vapour generated by heating the saturated steam obtained from boiling water. Results of computer simulations suggest that such a dishwasher would be able to kill 99 per cent of bacteria on one plate in just 25 seconds. As yet, the dishwasher only exists as a computer model, and not a physical object, but researchers say their study provides a basis for the development of next-generation dishwashers'.

We introduce a nonparametric graphical model for discrete node variables based on additive conditional independence. Additive conditional independence is a three way statistical relation that shares similar properties with conditional independence by satisfying the semi-graphoid axioms. Based on this relation we build an additive graphical model for discrete variables that does not suffer from the restriction of a parametric model such as the Ising model. We develop an estimator of the new graphical model via the penalized estimation of the discrete version of the additive precision operator and establish the consistency of the estimator under the ultrahigh-dimensional setting. Along with these methodological developments, we also exploit the properties of discrete random variables to uncover a deeper relation between additive conditional independence and conditional independence than previously known. The new graphical model reduces to a conditional independence graphical model under certain sparsity conditions. We conduct simulation experiments and analysis of an HIV antiretroviral therapy data set to compare the new method with existing ones.

By the year 2021, cybercrime losses will cost upwards of $6 trillion annually. It's no surprise, then, that the cybersecurity industry is exploding as it grows to protect the networks and systems on which companies and organizations operate and store data. Because effective information security requires smarter detection, many cybersecurity companies are upping their game by using artificial intelligence to achieve that goal. A new wave of AI-powered solutions and products keep bad actors on their toes while giving IT teams much needed relief. Here are 30 companies merging artificial intelligence and cybersecurity to make the virtual world safer.

It's a bright September morning in San Carlos, California, and Masayoshi Son, chairman of SoftBank, is throwing me off schedule. I'd come, as he had, to meet with the people he's tapped to run the Vision Fund, his $100 billion bet on the future of, well, everything. After almost four decades of building SoftBank into a telecom conglomerate, Son, an inveterate dealmaker, launched this unprecedented venture two years ago to back startups that he believes are driving a new wave of digital upheaval. He has staked everything on its success–his company, his reputation, his fortune. We'd both arrived with the same basic question: Where is this massive vehicle heading? But because I wasn't the one footing the 12-figure allowance, I understood that I'd be the one to wait. When I finally arrive at the Vision Fund's offices, just off California's Highway 101, I'm struck by how mundane they are. Son is known for big, showy statements. He reportedly paid $117 million for a home in Woodside in 2013, the highest price ever in the U.S. This glass and concrete building, on the other hand, could be found in any part of suburban America. The room where I wait is spartan.

SAN CARLOS, Calif., Jan. 14, 2019 (GLOBE NEWSWIRE) -- Check Point Software Technologies Ltd. (NASDAQ:CHKP), a leading provider of cyber security solutions globally, today announces it has acquired ForceNock Security Ltd. of Tel Aviv, Israel. Founded in 2017, ForceNock, developed a Web Application and API Protection (WAAP) technology which utilizes machine learning, behavioral and reputation-based security engines. Check Point plans to integrate ForceNock's technology into its Infinity total protection architecture. "Check Point is committed to providing the most comprehensive security architecture to prevent current and future generations of cyber attacks. The growing usage of platforms - Cloud, Network, Mobile, Endpoint and IoT - requires complete, simple to deploy and easy to use security technologies", said Dr. Dorit Dor, Check Point's VP Products. "Incorporating ForceNock's technology into our Infinity Architecture will enable us to continue to provide the highest level of security for our customers worldwide and strengthens our machine learning protection capabilities."

America's first autonomous robot farm launched last week, in the hopes that artificial intelligence (AI) can remake an industry facing a serious labor shortage and pressure to produce more crops. Claiming an ability to "grow 30 times more produce than traditional farms" on the strength of AI software, year-round, soilless hydroponic processes, and moving plants as they grow to efficiently use space, the San Carlos, California-based company Iron Ox aims to address some of the agricultural industry's biggest challenges. Such challenges have also caught the attention of investors, who made more than $10bn in investments last year, representing a 29% increase from 2016. In a 2,000-sq ft grow space, leafy greens and herbs are planted in individual pots housed in 4ft by 8ft white "grow modules", which weigh about 800lb. Autonomous machines do the heavy lifting, farming and sensing.

Brandon Alexander would like to introduce you to Angus, the farmer of the future. He's heavyset, weighing in at nearly 1,000 pounds, not to mention a bit slow. But he's strong enough to hoist 800-pound pallets of maturing vegetables and can move them from place to place on his own. Sure, Angus is a robot. But don't hold that against him, even if he looks more like a large tanning bed than C-3PO.

Brandon Alexander would like to introduce you to Angus, the farmer of the future. He's heavyset, weighing in at nearly 1,000 pounds, not to mention a bit slow. But he's strong enough to hoist 800-pound pallets of maturing vegetables and can move them from place to place on his own. Sure, Angus is a robot. But don't hold that against him, even if he looks more like a large tanning bed than C-3PO.