AMD Ryzen AI Embedded P100 series expands with up to 12 Zen 5 cores, 80 TOPS of AI performance
At CES 2026, we saw AMD launch its new Ryzen AI Embedded P100 series of SoCs, with four- and six-core models designed for Edge AI. At the time of writing, the lineup had six SKUs, with higher-core variants to be announced later. Now at Embedded World 2026, AMD has expanded the Ryzen AI Embedded P100 series with six additional SKUs available in commercial and industrial temperature grades, while the automotive-grade SoCs remain unchanged. The new SOCs integrate 8-12 Zen 5 CPU cores (upgrade from 4-6 cores ), RDNA 3.5 graphics, and an XDNA 2 NPU on a single chip to deliver up to 80 TOPS (upgrade from 50 TOPS) of combined/system AI performance AMD claims up to 39% higher multithreaded CPU performance and 2.1× higher total system TOPS compared to Ryzen Embedded 8000 Series. They support unified CPU-GPU memory, enabling low-latency processing for tasks such as multi-camera machine vision, Visual
Raspberry Pi CM0-based industrial AI camera features motorized auto-focus system, 12-pin Ethernet/RS-232/DO aviation connector
At Embedded World 2026 in Germany, EDATEC launched the ED-AIC1000, a compact industrial AI camera built around the Raspberry Pi CM0 and designed for machine vision and industrial automation applications, such as quality inspection, object detection, and production-line monitoring. It integrates a 1.3 MP global-shutter camera with a sampling rate of up to 120 FPS, along with motorized autofocus M12 lenses, and three independently configurable lighting zones for reliable imaging. The camera also integrates a 12-pin M12 industrial connector that provides 24 V power input, 100 Mbps Ethernet, RS-232, a trigger input, and an isolated digital output. The system supports H.264 encoding/decoding up to 1080p, consumes up to 24 W of power, and comes in a rugged aluminum enclosure measuring 67 × 46 × 46 mm, designed to operate in 0 °C to 60 °C environments. EDATEC ED-AIC1000 specifications: SoM – Raspberry Pi CM0 SoC – Broadcom BCM2710A1 CPU – Quad-core
University of Exeter: Wildlife imaging shows that AI models aren’t as smart as we think. “Marketing for AI imaging systems often suggests that models can easily tackle novel scenarios across ecosystems and settings, much in the same way as human observers. But in a new article, two University of Exeter researchers argue that this is based on a ‘flawed assumption’.”
https://rbfirehose.com/2026/03/07/university-of-exeter-wildlife-imaging-shows-that-ai-models-arent-as-smart-as-we-think/
University of Exeter: Wildlife imaging shows that AI models aren’t as smart as we think. “Marketing for AI imaging systems often suggests that models can easily tackle novel scenarios across …
edited by Michelle Cotton – Radical Software: Women, Art & Computing 1960–1991
#radicalsoftware #machinevision #neuralarchive #neuralmag #womenintechnology#mediaarthistory #digitalpioneers #digitalheritage #retrofuture #cyberfeminism #technofeminism #womenintech #feministfuture #datafeminism #femtech #artandtechnology #arttech #artandtech #audiovisualart #audiovisuals #interactiveart #newmediaart #newmediaartist #mediaart #mediaarts #mediaartist #digitalart #digitalartist #timebasedart #digitalaesthetics
Q42 Research: Expanding visual search for online art collections. “Ever wanted to find artworks containing a specific object? Like a particular vase, animal, or architectural element across an art collection? I made this a reality by combining two machine learning models during my graduation research project for Q42 and University of Applied Sciences Windesheim.”
https://rbfirehose.com/2026/01/27/q42-research-expanding-visual-search-for-online-art-collections/
Advantech SOM-6820 COM Express module is powered by Qualcomm Snapdragon X Elite Arm SoC
Advantech SOM-6820 is a COM Express Type 6 Compact Computer-on-Module powered by a Qualcomm Snapdragon X Elite SoC with up to twelve 64-bit Arm Oryon cores, instead of an x86 processor from Intel or AMD, more commonly found on COM Express modules. The COM also features up to 64GB LPDDR5 memory, two MIPI CSI camera connectors, an RTL8153B USB 3.0 Gigabit Ethernet controller, and a TPM 2.0 security chip. All I/Os are exposed through two standard 220-pin B2B connectors, including DisplayPort and LVDS/eDP interfaces for up to four 4K displays, up to four SATA III for storage, twelve USB 3.0/2.0 interfaces, multiple PCIe Gen4/3 interfaces, and more. With up to 45 TOPS of AI performance, the SOM-6820 is especially well-suited to medical imaging and machine vision applications as well as mission-critical systems and humanoid robots. Advancec SOM-6820 specifications: Snapdragon X Elite SoC variants (one or the other) X1E-00-1DE 12-core up
IEEE Spectrum: TraffickCam Uses Computer Vision to Counter Human Trafficking . “Abby Stylianou built an app that asks its users to upload photos of hotel rooms they stay in when they travel. It may seem like a simple act, but the resulting database of hotel room images helps Stylianou and her colleagues assist victims of human trafficking.”
Smidmart
cnx-software.com
ResearchBuzz: Firehose
Neural
