Machine learning news highlights the integration of AI algorithms into electronics design, enabling smarter systems in sectors like healthcare, automotive, and industrial automation. Embedded ML models enhance edge computing, sensor fusion, and predictive maintenance. Developments in hardware acceleration, neural processing units (NPUs), and low-power AI chips redefine electronics product development. For Electronics Weekly readers, machine learning coverage reveals how data-driven design, inference optimization, and intelligent systems are transforming component use, system architecture, and market differentiation.
TDK and Hokkaido University are to demonstrate real-time learning in a ‘reservoir’ analogue AI chip that mimics the cerebellum at CEATEC in Japan. Reservoir computing is not deep-learning, where there is an input layer, multiple hidden layers and an output layer, usually implemented in digital logic that executes many, sometime trillions, of multiply and add operations. “Reservoir computing consists of an ...
A single structure built in the metal layers of an IC can implement both machine learning and analogue AI inferencing, according to a French team led by Grenoble lab CEA-Leti – and the CMOS below can also be used for processing. Made between two metal interconnect layers, the structure has four layers: TiN at the bottom, Si-doped HfO2, a Ti ...
Analog Devices has teamed up with Antmicro to train two of ADI’s Cortex-M4 microcontollers to implement AI-at-the-edge. The key is Antmicro’s Visual Studio Code plug-in, which is built on its Kenning machine learning library. “Kenning’s aim is not to bring yet another training or compilation framework for deep learning models,” according to Antmicro. Kenning instead provides “a unified API that ...
F-Tac is a robot hand that can sense touch with 100μm resolution across 70% of its grasping surface, and can grasp using that touch feedback. “The spatial resolution combined with the enormous coverage are truly novel and were not possible previously,” claimed team member Professor Kaspar Althoefer (pictured), director of the Centre of Excellence Advanced Robotics at Queen Mary University, ...
Alif Semiconductor has integrated Arm’s Ethos-U85 neural processing unit (NPU) into its second generation of its ‘Ensemble’ microcontrollers for AI and machine learning. It is “the world’s first implementation of the Ethos-U85 in an endpoint AI MCU”, according to Arm IoT general manager Paul Williamson. “With Alif’s high bandwidth memory and power management, [the new parts] support NPU operators required ...
A bill to regulate the use of algorithms and automated decision making by public authorities has been proposed by the House of Lords. Lord Clement-Jones is behind the fledgling bill. He is co-founded and shares the chair of the ‘All party parliamentary group on AI’, is the former chair of the Lords Select Committee on AI, and is the author ...
SiFive has announced RISC-V core intellectual property for data centre processors. Called P870-D, it is an update of the non-data centre P870, with support added for AMBA CHI protocol. “By harnessing a standard CHI bus,” said SiFive, “the P870-D enables SiFive’s customers to scale up to 256 cores while harnessing industry-standard protocols including CXL [Compute Express Link] and CHI C2C [chip ...
San Francisco-based Particle has announced an octa-core Raspberry-Pi shaped single-board computer built around a Qualcomm Snapdragon Kryo CPU with 12Top/s neural processing capability, and equipped with 5G and Wi-Fi 6E comms. Called Tachyon, and aimed at AI edge processing, it is designed to run Ubuntu across its four 1.9GHz Arm cores, three 2.4GHz cores and single 2.7GHz core. Particle describes ...
The AI Hardware & Edge AI Summit is dedicated to the entire AI and ML ecosystem. The four-day event (9-12 September) consists of keynotes, presentations and workshops based on training, deploying and scaling ML systems that are fast, affordable and efficient.
Oak Ridge National Laboratory has curated an open-access on-line library of waveforms from the US power grid for power engineers wanting to apply AI techniques to grid monitoring and control. “Researchers can search different variables, like the type of sensor or a description of the event – for example, a waveform that represents a blown transformer and its effect on ...
