IT in Manufacturing


Neural Compute Stick for deep-learning projects

Technews Industry Guide: Industrial Internet of Things & Industry 4.0 IT in Manufacturing

RS Components has introduced the Intel Movidius Neural Compute Stick (NCS), the newest development tool for ultra-low-power deep-learning inference. The tool enables developers to develop and prototype artificial intelligence (AI) applications to a broad range of devices at the edge in a convenient USB form factor.

Targeting developers, corporate R&D and academic researchers working in machine-learning and data-science applications, the NCS integrates the Movidius Vision Processing Unit (VPU), which offers best-in-class power efficiency and is capable of running high-performance floating-point convolutional neural networks (CNNs).

Supporting the popular deep neural network (DNN) framework, the stick is ideal for use as a development tool for neural network prototyping and acceleration. The USB-form-factor inference engine enables developers and researchers to free their projects from the cloud and allow them to learn quickly about the performance and accuracy of their neural network applications running in the real world. Neural network projects can be quickly ported via the Movidius Neural Compute Compiler to run real-time deep-learning inference on the compact USB stick.

Enabling the acceleration of existing compute-constrained platforms, the NCS enables deep-learning R&D and prototyping on a Linux laptop or any x86-based host device. In addition, the Neural Compute Platform API allows user applications to run on an embedded host, which can initialise the target platform, load a graph file and offload inferences. Support for the NCS will also be extended in the future to include other platforms, such as the Raspberry Pi.

The complete list of software tools available in the Movidius Neural Compute Software Development Kit includes the Movidius Neural Compute toolkit and the Movidius Neural Compute API. These tools are available online on the developer.movidius.com website.

For more information contact RS Components SA, +27 (0)11 691 9300, [email protected], www.rsonline.co.za



Credit(s)



Share this article:
Share via emailShare via LinkedInPrint this page

Further reading:

RS South Africa is Master Distributor for Arduino platform
RS South Africa Industrial Computer Hardware
RS South Africa has been named Master Distributor for the Arduino UNO Q, reinforcing its position as a leading technology partner for engineers and developers across South Africa and the broader African region.

Read more...
Siemens ecosystem strengthens data and AI integration
Siemens South Africa IT in Manufacturing
Siemens has announced significant expansions to its Industrial Edge ecosystem, accelerating data and AI integration and releasing enhanced cybersecurity functionalities. These enable a seamless integration of IT and OT environments, optimise processes and reduce operational disruptions.

Read more...
Siemens manages shipbuilding process for HD Hyundai
Siemens South Africa IT in Manufacturing
Siemens has been selected by HD Korea Shipbuilding & Offshore Engineering as a preferred partner to establish an integrated platform to manage the entire shipbuilding process as a single data flow to help ensure consistency across all its global shipyard facilities.

Read more...
Transforming the process industry through digitalisation
Endress+Hauser South Africa IT in Manufacturing
By connecting field devices, systems and people, digitalisation creates new opportunities to optimise operations, enhance maintenance strategies and support continuous improvement. As a leading instrumentation provider and major source of process data, Endress+Hauser plays a key role in enabling this transformation.

Read more...
The OT operator’s guide to security and uptime on the plant
RJ Connect IT in Manufacturing
The article addresses three common questions about industrial network deployment and maintenance, exploring ways to achieve better control and visibility with more efficiency.

Read more...
The assets you can’t see are the ones that can shut you down
IT in Manufacturing
ABEGuardOT is an asset management solution that delivers continuous, non-intrusive visibility across multi-vendor environments, including Siemens, Rockwell, ABB, Honeywell, Schneider Electric, Emerson, GE and Yokogawa, with support for OPC UA, EtherNet/IP, Modbus and Profibus.

Read more...
Edge I/O NTS and the need for industrial speed
Schneider Electric South Africa IT in Manufacturing
One of the most compelling solutions to emerge from industrial automation is Edge I/O NTS, which represents a natural evolution of computing from centralised servers to localised, device-level input/output processing, offering improved speed, efficiency and resilience.

Read more...
The next wave of AI-driven process automation
Schneider Electric South Africa IT in Manufacturing
As process industries hurtle toward an AI-driven future, four powerful trends are set to redefine automation strategies in 2026: hyper automation, AI-first automation, low code/no code platforms, and advanced process intelligence.

Read more...
Huge increase in denial-of-service cyber threats
IT in Manufacturing
NETSCOUT has released its Distributed Denial-of-Service Threat Intelligence report, revealing sophisticated attacker collaboration, resilient botnets and compromised IoT infrastructure that drove more than eight million DDoS attacks worldwide.

Read more...
Sustainable manufacturing
ABB South Africa IT in Manufacturing
ABB’s production facility in Shandong province, China is delivering measurable energy and emissions reductions through the implementation of advanced digital energy management and electrification solutions.

Read more...









While every effort has been made to ensure the accuracy of the information contained herein, the publisher and its agents cannot be held responsible for any errors contained, or any loss incurred as a result. Articles published do not necessarily reflect the views of the publishers. The editor reserves the right to alter or cut copy. Articles submitted are deemed to have been cleared for publication. Advertisements and company contact details are published as provided by the advertiser. Technews Publishing (Pty) Ltd cannot be held responsible for the accuracy or veracity of supplied material.




© Technews Publishing (Pty) Ltd | All Rights Reserved