Deeplite platform accelerates AI on Arm CPUs through quantisation

CPU

Deeplite, a Canadian AI software company, has unveiled its Deeplite Runtime (DeepliteRT) platform that makes AI models smaller and faster without compromising accuracy.

Thanks to quantisation, customers will benefit from reduced power consumption and the ability to use existing Arm CPUs to run AI models with GPU-level performance.

AI optimisation’s importance is growing in an industry where edge devices are increasingly being turned to. Making AI models run on small...

NVIDIA unveils 200 trillion operations per second edge AI accelerator

NVIDIA

NVIDIA debuted the latest version in its AI accelerator series for robotics and edge devices at its GTC event on November 9, the Jetson AGX Orin.

The new model is built on NVIDIA’s Ampere architecture and can process up to 200 trillion operations per second, six times the capacity of its predecessor.

The company's Jetson series of products are used in a diverse range of edge and AI devices for a wide variety of use cases.

NVIDIA’s VP and general manager of...

Vecow and Blaize partner on workstation-grade edge AI

Vecow ECX-2400 AI

Vecow, an embedded PC company, is launching a new AI-powered edge computing solution in partnership with AI edge firm Blaize.

The Vecow ECX-2400 AI Computing System has been designed to use the Blaize Graph Streaming Processor (GSP) based Xplorer AI accelerator to deliver much improved AI performance with higher system reliability, lower power consumption, and faster time-to-market.

The system is intended for industrial applications such as smart AOI, public security,...

Andes Technology and Cyberon work together on edge-computing voice recognition

A man using voice recognition software on his smartphone.

Embedded speech solution provider, Cyberon, and Andes Technology, a supplier for high efficiency, low-power 32/64-bit RISC-V processor cores, have collaborated on the edge-computing voice recognition solution, Cyberon DSpotter.

As part of the partnership, the companies will explore Andes DSP-capable RISC-V CPU cores, such as D25F and comprehensive software development environment to provide a cost-effective, high performance, and easy-to-deploy solution.

The development...

National Science Foundation funds 11 AI-research institutes across US

Research with Microscope

The National Science Foundation (NSF), an independent government agency for the advancement of scientific research in the US, plans to fund eleven new AI-research institutes across the country.

Each institute will receive around $20 million (£14.4m) over five years from the NSF, with additional support coming from other government departments and partnered companies such as Amazon, Google, and Intel.

The expansion will mean National AI Research Institutes now spread...

XCO gains funding for chronic disease edge computing tech

A teddy in bed with a plaster on its head.

XCO Tech, a specialist in movement, biometric & cognition tracking technology, has confirmed it will receive advisory services and funding of up to $1m (£720,000) from the National Research Council of Canada Industrial Research Assistance Program (NRC IRAP) over three years.

The cash will be used to advance research and development of embedded AI-based technologies for chronic disease assessment and monitoring. 

The use of funds includes support of XCO's role...

CyberLink AI and ASUS edge computing unite for retail IoT solution

CyberLink FaceMe

CyberLink Corp., an AI and facial recognition company, has integrated its FaceMe AI facial recognition engine with ASUS's Tinker Board 2 computer to help improve security and contactless experiences in retail, public services, and hospitality.

CyberLink’s FaceMe developer kit is a cross-platform AI facial recognition engine ranked as one of the most accurate in the world. Optimised for IoT hardware, FaceMe seeks to bring highly accurate and flexible facial recognition...

Pratexo concludes multi million pound seed round for edge computing investment

Someone counting money in their hands.

Pratexo, a specialist in edge computing and distributed cloud platform for artificial intelligence (AI), Internet of Things (IoT) and Industry 4.0, has completed a $3.5 million (£2.54m) round of fundraising.

The company plans to use the money to accelerate its platform development and go-to-market efforts across North America and Europe.

Pratexo provides a technology platform to support IoT and artificial intelligence strategies and initiatives, which demand compute...

Nvidia unveils Fleet Command to scale edge AI services

Graphic of human mind depicting artificial intelligence.

Computer systems designer Nvidia has launched its Fleet Command managed edge AI services platform, which could help companies solve the problem of securely deploying and managing AI applications across thousands of locations.

Nvidia Fleet Command’s remote management software is said to let businesses securely roll out and manage their AI applications without sacrificing the real-time processing of edge computing. Specifically engineered to ease a company’s IT burden, Fleet...

US Postal Service to speed up package processing with edge computing

A US Postal Service mail box.

The US Postal Service (USPS) has been harnessing edge computing combined with AI to faster process the 7.3 billion parcels it deals with annually.

The organisation has implemented advanced computer systems at 195 of its mail processing centres throughout the USA to work on seven computer vision models, reducing the time required to track a missing package from numerous days to less than two hours.

A computer vision task that would previously have taken a fortnight on...