The ongoing global pandemic has created an urgent need for rapid tests that can diagnose the presence of the SARS-CoV-2 virus, the pathogen that causes COVID-19, and distinguish it from other respiratory viruses. Now, common respiratory from Japan have demonstrated a new system for single-virion identification of common respiratory pathogens using a machine learning algorithm trained on changes in current across silicon nanopores. This work may lead to fast and accurate screening tests for diseases like COVID-19 and influenza. In a study published this month in ACS Sensors scientists at Osaka University have introduced a new system using silicon nanopores sensitive enough to detect even a single virus particle when coupled with a machine learning algorithm. In this method, a silicon nitride layer just 50 nm thick suspended on a silicon wafer has tiny nanopores added, which are themselves only 300 nm in diameter.
IBM Corp. said today it's hoping to provide a standardized solution for developers to create and deploy machine learning models in production and make them portable to any cloud platform. To do so, it said it's open-sourcing the Kubeflow machine learning platform on Tekton, a continuous integration/continuous development platform developed by Google LLC. It's popular with developers who use Kubernetes to manage containerized applications, which can run unchanged across many computing environments. IBM said it created Kubeflow Pipelines on Tekton in response to the need for a more reliable solution for deploying, monitoring and governing machine learning models in production on any cloud platform. That's important, IBM says, because hybrid cloud models are rapidly becoming the norm for many enterprises that want to take advantage of the benefits of running their most critical business applications across distributed computing environments.
Autonomous vehicle startup Cruise has partnered with Walmart to deliver orders from a Scottsdale, AZ, Walmart store to local customers' homes, starting early next year. General Motors-backed autonomous vehicle startup Cruise has announced a partnership with Walmart to deliver orders from a Scottsdale, AZ, Walmart store to local customers' homes, starting early next year. Customers will be able to place orders to the store and have them delivered in one of Cruise's electric self-driving Chevy Bolts. If the pilot goes well, a Cruise spokesperson said, the company will mull launching on-demand delivery with other retailers in the future. Walmart has forged driverless vehicle delivery partnerships with other automakers and startups.
Imagination Technologies has launched a scalable neural network accelerator IP core optimised for automotive and autonomous systems but also aimed at industrial designs. The Series4 Neural Network Accelerator (NNA) core has been optimised for the YOLOv3 neural network framework, for processing large, rectangular images, rather than a general purpose execution unit. It is aimed at developer of system-on-chip devices for sensor fusion in high performance autonomous vehicles such as robotaxis, last mile delivery and automated street sweepers. The NNA core achieves 12.5TOPS of performance through 4096 multiply accumulate (MAC) units in 1mm2 on a 5nm process technology, all connected by a 256 network on chip (NOC). This that is over 20x faster than an embedded GPU and 1000x faster than an embedded CPU for AI inference says the company.
The brain's thalamus has historically been thought of as a relay centre that transmits sensory and motor inputs to the cortex for processing, or that transmits information from one part of the cortex to another. In 2017, three groups made the unexpected discovery that the thalamus also has a key role in short-term memory -- specifically, in maintaining the recurrent patterns of cortical activity that underlie memory1–3. However, the genetic basis of this role for the thalamus remained unexplored. Writing in Cell, Hsiao et al.4 reveal that the gene Gpr12 is key to thalamic maintenance of short-term memory. Their findings will have relevance for many fields, from cognitive therapeutics to artificial intelligence.
This story originally appeared in the December issue of Discover magazine as "Scientist in Toyland." It's easy to pin labels on Chuck Hoberman, but hard to stick with just one. He's a toymaker -- the brains behind the colorful, expanding Hoberman sphere, which you and your kids have been playing with since the early 1990s (and which earned a place in the Museum of Modern Art's permanent collection). Physically, he works sometimes from an airy room on the second floor of a house-turned-office-suite near Harvard Square in Cambridge, Massachusetts. The Cambridge office is tidy, with white walls and plenty of light. The surfaces are usually cleared, but today they're cluttered with the material expressions of his geometric dreams: Models made of two-dimensional pieces, hinged together to form 3D structures that deform, bend or otherwise fold in prescribed ways.
There's plenty of competition: VirtualAPT, based in Brooklyn, has robots that glide through homes and provide immersive virtual reality tours; REX, a brokerage in Woodland Hills, Calif., has an AI-trained robot to answer potential buyers' questions at open houses; RealFriend and OjoLabs have AI-powered chatbots that mimic human conversation while providing deeply personalized home listings and buying advice. In Zenny's case, the robot is powered remotely by the real estate broker or property manager who is handling the showing from afar. It is also equipped with sensors to keep it from running into walls or people. In addition to Zenny, Zenplace's platform includes a full suite of rental management solutions, including tenant screening, electronic lockboxes for on-demand property viewings, and a secure online portal for rent payment. The company charges a $599 flat fee for some properties, and $99 a month for others. VirtualAPT's robots, which roll through homes capturing 360-degree videos in 4K resolution, provide ultra-crisp, high-quality images.
From 4,675 fully labeled bear faces on DSLR photographs, taken from research and bear-viewing sites at Brooks River, Ala., and Knight Inlet, they randomly split images into training and testing data sets. Once trained from 3,740 bear faces, deep learning went to work "unsupervised," Dr. Clapham said, to see how well it could spot differences between known bears from 935 photographs. First, the deep learning algorithm finds the bear face using distinctive landmarks like eyes, nose tip, ears and forehead top. Then the app rotates the face to extract, encode and classify facial features. The system identified bears at an accuracy rate of 84 percent, correctly distinguishing between known bears such as Lucky, Toffee, Flora and Steve.
Our blood transports many chemicals besides oxygen and carbon dioxide. Some of these molecules provide useful indicators of the state of our health. Indeed, measuring such biomarkers is a common feature of clinical blood tests. Other molecules present, such as hormones and drugs, directly affect health by modulating processes such as metabolism and immune responses. Writing in Nature, Bar et al.1 shed light on the factors that affect the recipe for human blood's chemical brew.